© 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. 76148
    Prev
    Next
    INDEX
    Explanations

    terms related to game mechanics and balance changes

    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
     legally
    -0.06
     consort
    -0.06
     upgraded
    -0.06
    วร
    -0.06
     rejection
    -0.06
     Emb
    -0.06
    jur
    -0.06
    esen
    -0.06
     ol
    -0.06
    auen
    -0.06
    POSITIVE LOGITS
    ½æķ°
    0.07
    /Dk
    0.07
     balance
    0.07
    .balance
    0.07
    cala
    0.07
     ner
    0.06
    icions
    0.06
    ewing
    0.06
    >tag
    0.06
    epad
    0.06
    Activations Density 0.011%

    No Known Activations