© 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. 17-LLAMASCOPE-RES-131K
    11. 78703
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical data and formatting in tables

    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
    acias
    -0.07
    _TAC
    -0.07
     Ñĥк
    -0.06
    ails
    -0.06
    kker
    -0.06
    Äįást
    -0.06
    _tac
    -0.06
     sum
    -0.06
     indeb
    -0.06
    lobs
    -0.06
    POSITIVE LOGITS
    riter
    0.06
    789
    0.06
    orama
    0.06
    iyat
    0.06
    essim
    0.06
    untu
    0.06
    rollo
    0.05
    rese
    0.05
    452
    0.05
    ress
    0.05
    Activations Density 0.028%

    No Known Activations