© 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. 56065
    Prev
    Next
    INDEX
    Explanations

    elements related to political or historical events and conditions

    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
    egra
    -0.07
    dera
    -0.07
    @student
    -0.07
    ben
    -0.06
    .Reader
    -0.06
    ạch
    -0.06
     slip
    -0.06
    erk
    -0.06
    raid
    -0.06
    inz
    -0.06
    POSITIVE LOGITS
    jang
    0.07
    idon
    0.07
     Rap
    0.06
    vine
    0.06
    blick
    0.06
     Mig
    0.06
    yte
    0.06
    _initializer
    0.06
    çłģ
    0.06
    imits
    0.06
    Activations Density 0.009%

    No Known Activations