© 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. 84102
    Prev
    Next
    INDEX
    Explanations

    details about product conditions and specifications

    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
    nette
    -0.06
    legacy
    -0.06
    lags
    -0.06
    dre
    -0.05
    ardy
    -0.05
     Morgan
    -0.05
    Nullable
    -0.05
     underestimated
    -0.05
    uto
    -0.05
    appy
    -0.05
    POSITIVE LOGITS
     never
    0.10
     unused
    0.10
     virgin
    0.10
    unused
    0.09
    never
    0.09
     UNUSED
    0.09
     haven
    0.09
     untouched
    0.09
     Unused
    0.09
    æľª
    0.08
    Activations Density 0.036%

    No Known Activations