© 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. 30635
    Prev
    Next
    INDEX
    Explanations

    phrases and terms indicating evaluation or description of significance

    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
    ãģ£ãģį
    -0.07
    874
    -0.07
    559
    -0.07
    aÅŁ
    -0.07
    rej
    -0.07
    Lik
    -0.07
    brace
    -0.06
    ÑģоÑĢ
    -0.06
    afka
    -0.06
    ỳ
    -0.06
    POSITIVE LOGITS
    ]âĢı
    0.06
    iesz
    0.06
    Crit
    0.06
    âĢı
    0.06
    $MESS
    0.06
    rary
    0.06
    iol
    0.06
     Byl
    0.06
    .documentation
    0.06
     haven
    0.06
    Activations Density 0.025%

    No Known Activations