© 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. 3709
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific function calls in code-related text

    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
    renc
    -0.07
     seni
    -0.07
    ivent
    -0.07
     pev
    -0.07
    serter
    -0.07
    sert
    -0.06
    baugh
    -0.06
     dán
    -0.06
    одаÑĢ
    -0.06
    SES
    -0.06
    POSITIVE LOGITS
    ÎķÎĻ
    0.06
    omat
    0.06
     Garner
    0.06
    å¨
    0.06
    ãĥĥãĥĹ
    0.06
    .UTF
    0.06
    çĦ¶
    0.05
    LEGRO
    0.05
    .crop
    0.05
    *>&
    0.05
    Activations Density 0.052%

    No Known Activations