© 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. 76982
    Prev
    Next
    INDEX
    Explanations

    programming-related identifiers and concepts

    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
     nic
    -0.07
     Angeles
    -0.06
     w
    -0.06
    ÄĻp
    -0.06
     scaff
    -0.06
    uffy
    -0.05
    º
    -0.05
    peg
    -0.05
     ding
    -0.05
    jr
    -0.05
    POSITIVE LOGITS
    stva
    0.08
     muschi
    0.08
    adolu
    0.08
     –↵↵
    0.08
    adol
    0.07
    icari
    0.07
    arem
    0.07
    anke
    0.07
    ɵ
    0.07
    .bunifuFlatButton
    0.07
    Activations Density 0.215%

    No Known Activations