Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-32K
    6. 12552
    Prev
    Next
    INDEX
    Explanations

    references to economic inequality and corporate influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retty
    -0.15
    ustainable
    -0.15
    ernet
    -0.15
    _NT
    -0.14
    .osgi
    -0.14
    etter
    -0.14
    recated
    -0.14
    antino
    -0.14
    á»ĥn
    -0.14
    entina
    -0.14
    POSITIVE LOGITS
     corporations
    0.21
     Wall
    0.21
     profits
    0.20
    profits
    0.20
     wealthy
    0.19
     corporation
    0.19
     corporate
    0.18
     Wealth
    0.18
     Corporate
    0.18
     PROFITS
    0.18
    Activations Density 0.226%

    No Known Activations