© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    references to triangles in various mathematical contexts

    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
    bie
    -0.09
    _EOF
    -0.07
    ijo
    -0.07
    luk
    -0.07
    สาร
    -0.07
    633
    -0.07
    aping
    -0.07
    elling
    -0.07
    anne
    -0.07
    باÙĨ
    -0.07
    POSITIVE LOGITS
    -shaped
    0.14
     shaped
    0.09
    stery
    0.08
    å½¢
    0.08
    /oct
    0.08
    iceps
    0.07
    ectomy
    0.07
    /tr
    0.07
    /qu
    0.07
    -eyed
    0.07
    Activations Density 0.036%

    No Known Activations