© 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. 55881
    Prev
    Next
    INDEX
    Explanations

    numerical statistics or performance data

    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
    tfoot
    -0.07
     пÑĢоб
    -0.06
    vider
    -0.06
    984
    -0.06
    æ´
    -0.06
     Kaf
    -0.06
    emble
    -0.06
    abei
    -0.06
    [:]
    -0.06
    æ¸
    -0.06
    POSITIVE LOGITS
     shar
    0.07
    _logged
    0.06
    аÑĢÑı
    0.06
    аÑĤи
    0.06
     base
    0.06
    ased
    0.06
    asad
    0.06
    aga
    0.06
    sample
    0.05
    bus
    0.05
    Activations Density 0.003%

    No Known Activations