© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 12917
    Prev
    Next
    INDEX
    Explanations

    concepts related to empowerment and control over personal choices, particularly in reproductive health and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸Ľà¸£à¸°à¸ª
    -0.15
    azzi
    -0.14
    اÙģÙĤ
    -0.14
     unwind
    -0.13
    ookie
    -0.13
    /Register
    -0.13
    _fds
    -0.13
    inois
    -0.13
     sensitivity
    -0.13
     mixer
    -0.13
    POSITIVE LOGITS
     control
    0.40
     ownership
    0.35
     choice
    0.35
     choices
    0.35
     agency
    0.32
    control
    0.31
    -control
    0.31
     sovereignty
    0.31
     Control
    0.30
     empowerment
    0.30
    Activations Density 0.216%

    No Known Activations