© 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. 17-LLAMASCOPE-RES-131K
    11. 91879
    Prev
    Next
    INDEX
    Explanations

    monetary values and statistics related to costs or funding

    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
    uraa
    -0.09
    immel
    -0.07
    άνÏī
    -0.07
    éĢļãĤĬ
    -0.07
    alu
    -0.07
    ruba
    -0.07
    lli
    -0.07
    /Instruction
    -0.07
     mili
    -0.07
    AGO
    -0.07
    POSITIVE LOGITS
     each
    0.14
    each
    0.11
     má»Ĺi
    0.10
     per
    0.10
     EACH
    0.09
     every
    0.09
     cada
    0.09
     Each
    0.09
    æ¯ı
    0.09
    Each
    0.09
    Activations Density 0.037%

    No Known Activations