© 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. 126394
    Prev
    Next
    INDEX
    Explanations

    references to maintaining focus or staying on topic

    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
    ¢
    -0.07
    ondo
    -0.07
    ÅĻez
    -0.07
    -major
    -0.07
    OfYear
    -0.07
    ifar
    -0.07
    asd
    -0.06
     Bilim
    -0.06
    RAP
    -0.06
    alley
    -0.06
    POSITIVE LOGITS
    ichi
    0.06
     transit
    0.06
     Merc
    0.06
     labor
    0.06
    undef
    0.06
    .avi
    0.05
    prech
    0.05
     <+
    0.05
    <$
    0.05
     kind
    0.05
    Activations Density 0.000%

    No Known Activations