© 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. 82891
    Prev
    Next
    INDEX
    Explanations

    proper nouns and named entities 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
    .intellij
    -0.10
    .jms
    -0.08
    abcdefghijklmnop
    -0.08
    _Lean
    -0.08
    agina
    -0.08
    otton
    -0.08
    uluk
    -0.07
    iteDatabase
    -0.07
    JKLM
    -0.07
    taboola
    -0.07
    POSITIVE LOGITS
     said
    0.08
     saying
    0.08
    :↵
    0.07
    igar
    0.06
    0.06
    ivo
    0.06
    idelberg
    0.06
     reference
    0.06
    k
    0.06
    riot
    0.06
    Activations Density 0.016%

    No Known Activations