© 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. 95922
    Prev
    Next
    INDEX
    Explanations

    references to various types of collections or compilations in the context of creative works

    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
    ÙĨس
    -0.08
    каÑģ
    -0.07
    eri
    -0.07
     Avery
    -0.07
    eless
    -0.07
    hlas
    -0.07
    /people
    -0.07
    antage
    -0.07
    /users
    -0.06
     architekt
    -0.06
    POSITIVE LOGITS
     of
    0.08
    -style
    0.08
    tures
    0.07
    /lists
    0.07
    -format
    0.07
    -type
    0.07
    PILE
    0.07
    -wide
    0.07
    LEM
    0.07
     ÏĦÏīν
    0.07
    Activations Density 0.021%

    No Known Activations