© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85873
    Prev
    Next
    INDEX
    Explanations

    references to trailers for movies or shows

    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
    esModule
    -0.07
     Keystone
    -0.06
    vit
    -0.06
    Ùħا
    -0.06
     trùng
    -0.06
    iker
    -0.06
    ello
    -0.06
    erness
    -0.06
    vÃŃ
    -0.06
    mass
    -0.06
    POSITIVE LOGITS
    lap
    0.07
    izzo
    0.07
    nested
    0.07
    ized
    0.06
    hots
    0.06
    AGMENT
    0.06
    ization
    0.06
    ised
    0.06
     Stokes
    0.06
    landa
    0.06
    Activations Density 0.003%

    No Known Activations