© 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. 71401
    Prev
    Next
    INDEX
    Explanations

    references to journalistic or literary achievements and publications

    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
    807
    -0.07
    sic
    -0.06
    arend
    -0.06
    UTTON
    -0.06
    thren
    -0.06
     Arrow
    -0.06
    åİ
    -0.06
    İ
    -0.06
    871
    -0.06
     Flake
    -0.06
    POSITIVE LOGITS
    uning
    0.07
     publications
    0.07
     widely
    0.07
     Columns
    0.07
    allas
    0.06
     Mothers
    0.06
     elsewhere
    0.06
    udu
    0.06
    lien
    0.06
     regularly
    0.06
    Activations Density 0.005%

    No Known Activations