© 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. 9-LLAMASCOPE-RES-131K
    11. 95542
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research institutions and their affiliations

    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
    anian
    -0.07
    ombok
    -0.06
    SID
    -0.06
    axy
    -0.06
    bob
    -0.06
    edo
    -0.06
    arsi
    -0.06
    .TODO
    -0.06
    fid
    -0.06
    ekil
    -0.06
    POSITIVE LOGITS
    segue
    0.06
    piler
    0.06
     stor
    0.06
    rs
    0.06
    xious
    0.06
    /state
    0.06
    zers
    0.06
    /memory
    0.06
    .cells
    0.06
    viso
    0.06
    Activations Density 0.006%

    No Known Activations