© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118950
    Prev
    Next
    INDEX
    Explanations

    discussions focused on political theories and their implications

    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
     regularization
    -0.08
     optionally
    -0.07
    åĿı
    -0.06
     regular
    -0.06
    ppv
    -0.06
     nightly
    -0.06
    regular
    -0.06
    CJK
    -0.06
    è¼Ķ
    -0.06
    _regular
    -0.06
    POSITIVE LOGITS
     Bracket
    0.07
    crit
    0.07
     Crit
    0.07
    Łèĥ½
    0.07
     зак
    0.07
    еÑī
    0.07
    VL
    0.07
    iod
    0.07
     Critics
    0.07
    tiv
    0.07
    Activations Density 0.002%

    No Known Activations