© 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. 121514
    Prev
    Next
    INDEX
    Explanations

    references to organizations and institutions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    roud
    -0.07
    strom
    -0.07
    abad
    -0.06
    acher
    -0.06
    ál
    -0.06
     пÑĢов
    -0.06
    anto
    -0.06
    शन
    -0.06
    ster
    -0.06
    POOL
    -0.06
    POSITIVE LOGITS
     called
    0.20
    called
    0.18
     Called
    0.17
    Called
    0.16
    åı«
    0.14
    -called
    0.13
     llam
    0.13
     known
    0.11
    known
    0.11
    ìĿ¸
    0.11
    Activations Density 0.254%

    No Known Activations