© 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 EvalsExportsAPI 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. 84246
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and their occurrences in the text

    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
    ecer
    -0.07
    orth
    -0.07
    .TabStop
    -0.06
    ãģ³
    -0.06
    >Lorem
    -0.06
     Zhou
    -0.06
    hil
    -0.06
    robat
    -0.06
    oko
    -0.06
    iore
    -0.06
    POSITIVE LOGITS
    utterstock
    0.10
    ystack
    0.07
    _HC
    0.07
    estring
    0.07
    ScreenWidth
    0.06
     dia
    0.06
    PermissionsResult
    0.06
    ãĥįãĥ«
    0.06
     stock
    0.06
     nuest
    0.06
    Activations Density 0.012%

    No Known Activations