© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80020
    Prev
    Next
    INDEX
    Explanations

    references to data presentation and statistical analysis

    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
    trim
    -0.07
     trim
    -0.07
    inci
    -0.06
    isel
    -0.06
     Trim
    -0.06
    eps
    -0.06
    quarter
    -0.06
    ans
    -0.06
    Sibling
    -0.06
    amic
    -0.06
    POSITIVE LOGITS
     paren
    0.12
    æĭ¬
    0.10
    paren
    0.10
     parentheses
    0.09
     brackets
    0.09
     parenthesis
    0.09
     bracket
    0.08
     paran
    0.08
     beside
    0.08
    Paren
    0.08
    Activations Density 0.092%

    No Known Activations