© 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. 61204
    Prev
    Next
    INDEX
    Explanations

    references to community service and contributions

    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
    endor
    -0.07
    urr
    -0.07
     overlay
    -0.06
    è·ĿéĽ¢
    -0.06
    undle
    -0.06
    meric
    -0.06
    udes
    -0.06
    íĥķ
    -0.06
    ĥĿ
    -0.06
     unless
    -0.06
    POSITIVE LOGITS
    sthrough
    0.08
    olik
    0.07
    _inches
    0.07
    during
    0.07
    emon
    0.07
     ActiveForm
    0.07
    rief
    0.07
    icularly
    0.07
     during
    0.07
    -IS
    0.06
    Activations Density 0.022%

    No Known Activations