© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98897
    Prev
    Next
    INDEX
    Explanations

    references to historical designations or listings

    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
    angan
    -0.06
    310
    -0.05
    -0.05
    ang
    -0.05
    apult
    -0.05
    end
    -0.05
    ijk
    -0.05
    ini
    -0.05
    gium
    -0.05
    inks
    -0.05
    POSITIVE LOGITS
    enler
    0.08
    inear
    0.08
    rtle
    0.08
    radan
    0.07
    .scalablytyped
    0.07
    PILE
    0.07
    lexport
    0.07
    erable
    0.07
    iales
    0.07
    æij©
    0.07
    Activations Density 0.000%

    No Known Activations