© 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. 83985
    Prev
    Next
    INDEX
    Explanations

    statements regarding regulatory or safety assessments related to health risks

    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
    uel
    -0.06
    ádu
    -0.06
     yes
    -0.06
    èĶµ
    -0.06
    olla
    -0.06
     quoi
    -0.06
    til
    -0.06
    aign
    -0.06
    _union
    -0.06
    uddle
    -0.06
    POSITIVE LOGITS
    podob
    0.07
     Dana
    0.07
    _DIP
    0.06
    reason
    0.06
     handjob
    0.06
     cần
    0.06
     beled
    0.06
     desea
    0.06
    usercontent
    0.06
     Spin
    0.06
    Activations Density 0.009%

    No Known Activations