© 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. 87791
    Prev
    Next
    INDEX
    Explanations

    references to unspecified subjects or general items

    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
    okit
    -0.08
    laughter
    -0.06
    ohan
    -0.06
    elier
    -0.06
    orph
    -0.06
    èĬ³
    -0.06
    CTL
    -0.06
     anywhere
    -0.06
    ctl
    -0.06
    ж
    -0.06
    POSITIVE LOGITS
     Learned
    0.07
    bjerg
    0.07
    stan
    0.07
    ?}",
    0.06
    wake
    0.06
    rosso
    0.06
    enberg
    0.06
    üh
    0.06
    iny
    0.06
     things
    0.06
    Activations Density 0.016%

    No Known Activations