© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4071
    Prev
    Next
    INDEX
    Explanations

    scholarly affiliations and institutional information

    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
    isz
    -0.07
    侯
    -0.07
    ÃŃž
    -0.07
    Äħ
    -0.06
     Bellev
    -0.06
    -slide
    -0.06
    holm
    -0.06
    aghetti
    -0.06
     IsNot
    -0.06
    ;;;;;;;;;;;;;;;;
    -0.06
    POSITIVE LOGITS
    drs
    0.07
    /embed
    0.07
    lij
    0.07
    LU
    0.07
    (Expected
    0.07
    rob
    0.07
     tails
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
     clusters
    0.06
     Verfüg
    0.06
    Activations Density 0.007%

    No Known Activations