© 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 EvalsExportsinterp-engineNEWAPI 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. 5551
    Prev
    Next
    INDEX
    Explanations

    elements related to media and entertainment topics

    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
     the
    -0.07
     van
    -0.07
    CKER
    -0.06
    eprom
    -0.06
     c
    -0.06
     sp
    -0.06
    oreach
    -0.06
     имÑĥ
    -0.06
    ature
    -0.06
    až
    -0.06
    POSITIVE LOGITS
    enti
    0.07
    enties
    0.07
    ennent
    0.07
    utut
    0.07
    iedade
    0.07
    asso
    0.07
    ียà¸Ķ
    0.06
    é½
    0.06
    557
    0.06
    emo
    0.06
    Activations Density 1.059%

    No Known Activations