© 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. 5661
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing and data storage

    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
    ssc
    -0.08
    åīĽ
    -0.07
    LogLevel
    -0.07
     La
    -0.07
    procs
    -0.07
    #echo
    -0.07
     Bain
    -0.07
    à¹Īà¹Ģà¸Ľ
    -0.06
    γκα
    -0.06
    [port
    -0.06
    POSITIVE LOGITS
     limitation
    0.07
     limits
    0.07
    _limit
    0.07
     limit
    0.07
    éĻIJ
    0.07
    .max
    0.07
    _max
    0.07
    ove
    0.07
     limitations
    0.06
    limits
    0.06
    Activations Density 0.026%

    No Known Activations