© 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. 5-LLAMASCOPE-RES-131K
    11. 126620
    Prev
    Next
    INDEX
    Explanations

    escape characters or backslashes in code or text

    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
    ìķ½
    -0.08
    utomation
    -0.08
    опол
    -0.08
    ectl
    -0.08
    олом
    -0.08
    /umd
    -0.07
    ScrollIndicator
    -0.07
    GenericType
    -0.07
    las
    -0.07
    HandlerContext
    -0.07
    POSITIVE LOGITS
    s
    0.06
    oran
    0.06
    itere
    0.06
    .mov
    0.06
     precursor
    0.06
     Dag
    0.06
    Âł
    0.06
     iter
    0.05
     Jun
    0.05
     counted
    0.05
    Activations Density 0.004%

    No Known Activations