© 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. 126332
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names and locations

    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
    adia
    -0.07
    ford
    -0.06
    cky
    -0.06
    lette
    -0.06
    aq
    -0.06
    ÃŃd
    -0.06
    izu
    -0.06
    .feed
    -0.06
    tte
    -0.06
    ppard
    -0.06
    POSITIVE LOGITS
     Beitrag
    0.07
     Silva
    0.06
    ANGED
    0.06
    testdata
    0.06
    REATED
    0.06
    <typeof
    0.06
    UTTON
    0.06
    agram
    0.06
    letcher
    0.06
    engin
    0.06
    Activations Density 0.017%

    No Known Activations