© 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. 15-LLAMASCOPE-RES-131K
    11. 103786
    Prev
    Next
    INDEX
    Explanations

    references to specific academic citations or statistical data

    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
    olet
    -0.08
    abra
    -0.07
    hsi
    -0.07
    .Annotation
    -0.07
    apo
    -0.07
    lse
    -0.07
    apult
    -0.07
    rons
    -0.07
    οκ
    -0.07
    //{{
    -0.07
    POSITIVE LOGITS
     Hell
    0.06
    iss
    0.06
     Ple
    0.06
    νÏī
    0.06
    ?type
    0.06
    ?page
    0.06
    ennes
    0.06
    åķ
    0.05
     Cooler
    0.05
     Harley
    0.05
    Activations Density 0.007%

    No Known Activations