© 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. 72039
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate a connection or relationship between ideas

    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
    гл
    -0.07
    wner
    -0.06
    .Volume
    -0.06
    templ
    -0.06
    inger
    -0.06
    ibility
    -0.06
    ixa
    -0.06
    CHAN
    -0.06
    gency
    -0.06
    ENTS
    -0.06
    POSITIVE LOGITS
    enie
    0.07
    é¡
    0.07
     Shed
    0.06
    ome
    0.06
     Establishment
    0.06
    _TS
    0.06
    rog
    0.06
    usal
    0.06
    enus
    0.06
    askell
    0.06
    Activations Density 0.022%

    No Known Activations