© 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. 94129
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and figures

    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
    isia
    -0.08
    semicolon
    -0.08
    rollable
    -0.08
    ãĥ³ãĥ
    -0.08
    ectl
    -0.07
    elters
    -0.07
    rame
    -0.07
    ollapsed
    -0.07
     aalborg
    -0.07
    åº
    -0.07
    POSITIVE LOGITS
    finger
    0.07
     send
    0.06
     representations
    0.06
     envoy
    0.06
     Representation
    0.06
    iator
    0.06
     representing
    0.06
     visit
    0.06
    bare
    0.06
    ent
    0.06
    Activations Density 0.004%

    No Known Activations