© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62060
    Prev
    Next
    INDEX
    Explanations

    references to categories and classifications, often indicated by structured labels or identifiers

    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
    辺
    -0.08
    ?url
    -0.07
    ,...↵↵
    -0.07
    uzu
    -0.07
    ombat
    -0.07
     ``(
    -0.07
    .Helper
    -0.07
    ussy
    -0.07
     att
    -0.07
    ModifiedDate
    -0.07
    POSITIVE LOGITS
    anner
    0.07
    iores
    0.07
    NR
    0.06
    ·
    0.06
    (er
    0.06
    iyan
    0.06
    ekyll
    0.06
    度
    0.06
    ien
    0.06
    nement
    0.06
    Activations Density 0.021%

    No Known Activations