© 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. 78626
    Prev
    Next
    INDEX
    Explanations

    references to visitor experiences and recommendations

    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
    ActionTypes
    -0.06
     Fey
    -0.06
    amaz
    -0.06
     churn
    -0.06
    bounding
    -0.06
    CustomLabel
    -0.05
    )["
    -0.05
    ozy
    -0.05
    ackages
    -0.05
    çµĦ
    -0.05
    POSITIVE LOGITS
    irectory
    0.08
    -directory
    0.08
    gebn
    0.08
    .Directory
    0.07
    ule
    0.07
    aight
    0.07
     directory
    0.07
    directory
    0.07
     Directory
    0.07
    vos
    0.07
    Activations Density 0.003%

    No Known Activations