© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103528
    Prev
    Next
    INDEX
    Explanations

    references to young adult and children's literature

    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
    ered
    -0.06
    sel
    -0.06
    sz
    -0.06
    Ñĩини
    -0.06
    ivil
    -0.06
    upy
    -0.06
     pregnant
    -0.06
    eless
    -0.06
    /configuration
    -0.06
    aby
    -0.06
    POSITIVE LOGITS
    yb
    0.07
    ickers
    0.07
     λο
    0.07
    /ad
    0.07
    лод
    0.06
     kategor
    0.06
     Mädchen
    0.06
    éĺħ
    0.06
    (children
    0.06
    ughter
    0.06
    Activations Density 0.027%

    No Known Activations