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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87331
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "as."

    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
    LastError
    -0.06
     Talent
    -0.06
    swana
    -0.06
     lev
    -0.06
    BT
    -0.06
     Stem
    -0.06
    achu
    -0.06
    tera
    -0.06
    ohn
    -0.06
    åľ³
    -0.06
    POSITIVE LOGITS
    close
    0.07
    cert
    0.07
     setFrame
    0.06
    _close
    0.06
    ancer
    0.06
    qrt
    0.06
    Binding
    0.06
    chez
    0.06
    noinspection
    0.06
    sembles
    0.06
    Activations Density 0.016%

    No Known Activations