© 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. 125911
    Prev
    Next
    INDEX
    Explanations

    references to knowledge, understanding, and emotional responses to knowledge

    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
    ene
    -0.07
    kin
    -0.07
    ter
    -0.07
    tera
    -0.07
    il
    -0.06
    to
    -0.06
    g
    -0.06
    ken
    -0.06
    az
    -0.06
    cell
    -0.06
    POSITIVE LOGITS
     Shadow
    0.07
    bine
    0.07
    auga
    0.07
    lamaz
    0.07
    лем
    0.07
    imli
    0.07
    -ignore
    0.07
     shadow
    0.07
    /filepath
    0.07
    -urlencoded
    0.07
    Activations Density 0.002%

    No Known Activations