© 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. 129160
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    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
    .ElementAt
    -0.06
     login
    -0.06
     Craig
    -0.06
     Sche
    -0.06
    /Delete
    -0.05
    orrar
    -0.05
    Äĥr
    -0.05
    inkel
    -0.05
    _WAKE
    -0.05
     Obrázky
    -0.05
    POSITIVE LOGITS
    ãĤĵãģª
    0.07
    .Guna
    0.07
    agan
    0.07
    eview
    0.07
    .bunifuFlatButton
    0.07
     geil
    0.07
    krom
    0.07
    ero
    0.07
    agra
    0.07
    ivot
    0.07
    Activations Density 0.004%

    No Known Activations