© 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. 16656
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements within programming languages

    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
    CTL
    -0.06
     offsetof
    -0.06
    offsetof
    -0.06
    lien
    -0.06
    ------+------+
    -0.06
    )((((
    -0.06
     rad
    -0.05
    еÑĢб
    -0.05
    $MESS
    -0.05
    DialogTitle
    -0.05
    POSITIVE LOGITS
    ÑĥÑĢа
    0.07
    rzy
    0.07
    yla
    0.07
    ãĤıãģĽ
    0.07
    insky
    0.07
    .onNext
    0.07
     dó
    0.07
     koc
    0.07
    jedn
    0.06
    azon
    0.06
    Activations Density 0.029%

    No Known Activations