© 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. 81523
    Prev
    Next
    INDEX
    Explanations

    citation and reference formatting elements

    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
    reur
    -0.06
    standing
    -0.06
    ugu
    -0.06
    aut
    -0.06
    лиз
    -0.06
     Springer
    -0.06
     Huffman
    -0.06
    irmed
    -0.06
    monic
    -0.06
    era
    -0.05
    POSITIVE LOGITS
    ÅĻet
    0.08
    ãĥ¥
    0.08
    ngo
    0.07
    ستÛĮ
    0.07
    kest
    0.07
    _bias
    0.07
    ceso
    0.07
    jev
    0.07
    acular
    0.07
    anela
    0.07
    Activations Density 0.002%

    No Known Activations