© 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. 17-LLAMASCOPE-RES-131K
    11. 69554
    Prev
    Next
    INDEX
    Explanations

    key nouns and their associated descriptors or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (![
    -0.07
    zelf
    -0.07
    ormap
    -0.06
    WindowTitle
    -0.06
    olatile
    -0.06
    .pm
    -0.06
    avan
    -0.06
    '=>"
    -0.06
    chedulers
    -0.06
    asil
    -0.06
    POSITIVE LOGITS
    kowski
    0.08
    uma
    0.07
    DSA
    0.06
    pcb
    0.06
    azu
    0.06
    cki
    0.06
    ?
    0.06
    ?:
    0.06
    rego
    0.06
    ****************************************************************************
    0.06
    Activations Density 0.178%

    No Known Activations