© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 9218
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to uncertainty and societal expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.33
    phans
    -0.24
    eur
    -0.19
    ımıza
    -0.18
    sing
    -0.18
    sembl
    -0.18
    subclass
    -0.17
    pires
    -0.17
    eus
    -0.17
    sembles
    -0.17
    POSITIVE LOGITS
    gether
    0.73
    adays
    0.57
    oretical
    0.49
    etheless
    0.48
    alog
    0.46
    atre
    0.45
    oret
    0.45
    ÑįÑĤомÑĥ
    0.44
    bidden
    0.43
    self
    0.43
    Activations Density 0.331%

    No Known Activations