© 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. 105365
    Prev
    Next
    INDEX
    Explanations

    instances of categorized subjects or tags related to specific content

    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
     appropri
    -0.07
    .Net
    -0.07
    ~
    -0.06
    ETF
    -0.06
    ÃIJ
    -0.06
    ково
    -0.06
    hus
    -0.06
    áo
    -0.06
    eres
    -0.06
    edor
    -0.06
    POSITIVE LOGITS
    hoot
    0.07
    rium
    0.07
    ILED
    0.07
    OLUMN
    0.07
    s
    0.07
    ylvania
    0.07
    malink
    0.07
     recurring
    0.06
    ged
    0.06
    .localization
    0.06
    Activations Density 0.007%

    No Known Activations