© 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. 27260
    Prev
    Next
    INDEX
    Explanations

    references to programs and systems related to loans and healthcare initiatives

    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
    мÑı
    -0.07
    uum
    -0.06
    raq
    -0.06
    rif
    -0.06
    rlen
    -0.06
    UDO
    -0.06
     Junk
    -0.06
     Brock
    -0.06
    amage
    -0.06
    azi
    -0.06
    POSITIVE LOGITS
    .utf
    0.06
    ÂĤ
    0.06
    ToFit
    0.06
    è³ĩ
    0.05
    avan
    0.05
    Pitch
    0.05
    SetTitle
    0.05
    tering
    0.05
    Rated
    0.05
     nackte
    0.05
    Activations Density 0.020%

    No Known Activations