© 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. 78683
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the concept of "impact."

    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
    eton
    -0.08
    AXB
    -0.08
     meille
    -0.07
    chwitz
    -0.07
    ixel
    -0.07
    blr
    -0.07
    rzy
    -0.07
    fty
    -0.07
    minus
    -0.07
    jac
    -0.07
    POSITIVE LOGITS
     Factor
    0.07
     upon
    0.07
     legalized
    0.07
     factors
    0.07
     Coy
    0.06
     Factors
    0.06
     pedals
    0.06
    ill
    0.06
     globalization
    0.06
    Factor
    0.06
    Activations Density 0.021%

    No Known Activations