© 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. 106310
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    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
    оÑĢаз
    -0.08
    .Invariant
    -0.07
    ÏĦά
    -0.07
    _ASSUME
    -0.07
    æ¨ĵ
    -0.07
     atan
    -0.07
    .Throw
    -0.06
    eec
    -0.06
     oÄį
    -0.06
    okoj
    -0.06
    POSITIVE LOGITS
    awai
    0.08
     Yes
    0.06
     rev
    0.06
    encil
    0.06
     Parr
    0.06
    /firebase
    0.06
    Yes
    0.06
    ist
    0.06
     yes
    0.06
    anova
    0.06
    Activations Density 0.001%

    No Known Activations