© 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. 76734
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation marks, particularly in numerical or technical contexts

    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
     mas
    -0.06
    inger
    -0.06
    ()>↵
    -0.06
    ergy
    -0.06
    æĪ¸
    -0.06
    DBG
    -0.06
    .↵
    -0.06
    -law
    -0.05
    rella
    -0.05
     Cloth
    -0.05
    POSITIVE LOGITS
    iVar
    0.08
    kart
    0.07
    .LENGTH
    0.07
     ofType
    0.07
    -valu
    0.07
    èĬ¯
    0.07
    erno
    0.07
    =size
    0.06
     manufact
    0.06
    RET
    0.06
    Activations Density 0.000%

    No Known Activations