© 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. 78664
    Prev
    Next
    INDEX
    Explanations

    marker-like symbols or lists that indicate items or categories

    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
    piel
    -0.06
     wr
    -0.06
    erts
    -0.06
    udo
    -0.06
    itarian
    -0.06
    anuts
    -0.06
    atham
    -0.06
    óst
    -0.06
    ennon
    -0.05
    uye
    -0.05
    POSITIVE LOGITS
    APH
    0.07
    onom
    0.06
    âĹİ
    0.06
    /GPL
    0.06
    _CAPACITY
    0.06
    ÏĦιÏĥ
    0.06
    æ±Ĺ
    0.06
     sieve
    0.06
    raman
    0.06
    Gear
    0.06
    Activations Density 0.005%

    No Known Activations