© 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. 106905
    Prev
    Next
    INDEX
    Explanations

    titles and descriptions of television shows and films

    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
    hir
    -0.07
    umbnails
    -0.06
    è§Ĥçľĭ
    -0.06
    ัà¸ĩà¸Ļ
    -0.06
    formance
    -0.06
    ozilla
    -0.06
    ifest
    -0.06
    rych
    -0.06
    cé
    -0.06
    .Optional
    -0.06
    POSITIVE LOGITS
     project
    0.09
     tent
    0.08
     unnamed
    0.07
    tent
    0.07
    yk
    0.06
     projects
    0.06
     deal
    0.06
     unspecified
    0.06
     next
    0.06
    project
    0.06
    Activations Density 0.019%

    No Known Activations