© 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. 78588
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and statutory regulations

    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
    ObjectContext
    -0.06
     Dao
    -0.06
     Russo
    -0.06
    tons
    -0.06
    immers
    -0.06
     length
    -0.06
    etically
    -0.05
    ether
    -0.05
    elier
    -0.05
    _COMPILER
    -0.05
    POSITIVE LOGITS
    Ă
    0.09
    See
    0.08
     See
    0.08
     Cf
    0.07
    NEY
    0.07
    pill
    0.07
     https
    0.07
    https
    0.07
    UTO
    0.07
    uto
    0.07
    Activations Density 0.043%

    No Known Activations