© 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. 129068
    Prev
    Next
    INDEX
    Explanations

    statistical data related to sports performances

    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
    еви
    -0.07
     McInt
    -0.06
    ãĤ¤ãĥ¤
    -0.06
     Barker
    -0.06
     ADM
    -0.06
    _die
    -0.06
    .Invariant
    -0.06
    eyin
    -0.06
    ÛĮزÛĮ
    -0.06
     Marl
    -0.05
    POSITIVE LOGITS
    iri
    0.07
    bes
    0.06
     Torrent
    0.06
    _blk
    0.06
    å¥Ī
    0.06
    nek
    0.06
    æĻ¶
    0.06
    èĥ¡
    0.06
    ae
    0.06
    ç½
    0.06
    Activations Density 0.029%

    No Known Activations