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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75205
    Prev
    Next
    INDEX
    Explanations

    terms related to vandalism and theft

    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
    inou
    -0.08
    enaire
    -0.07
    inars
    -0.07
    yles
    -0.07
    irie
    -0.07
     architekt
    -0.07
     Walton
    -0.07
    lify
    -0.07
    ãĥĮ
    -0.07
    ald
    -0.07
    POSITIVE LOGITS
    ously
    0.07
    -proof
    0.07
    fre
    0.07
    ishly
    0.07
    ERS
    0.07
    ous
    0.06
    uet
    0.06
    punk
    0.06
    -free
    0.06
    æİī
    0.06
    Activations Density 0.018%

    No Known Activations