© 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. 17-LLAMASCOPE-RES-131K
    11. 127133
    Prev
    Next
    INDEX
    Explanations

    occurrences of swearing and references to alcohol consumption

    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
    ãĥĸãĥŃ
    -0.09
     внеÑģ
    -0.08
     tắc
    -0.07
    renom
    -0.07
     cÃłng
    -0.07
     LUA
    -0.07
    _WE
    -0.07
     pornos
    -0.07
     pornô
    -0.06
    icie
    -0.06
    POSITIVE LOGITS
     several
    0.08
    Ñĥмов
    0.07
     mentions
    0.07
     mention
    0.07
    mentions
    0.07
     lots
    0.07
     although
    0.07
     references
    0.07
     very
    0.06
     sustained
    0.06
    Activations Density 0.013%

    No Known Activations