© 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. 71339
    Prev
    Next
    INDEX
    Explanations

    mentions of groups and their dynamics in various contexts

    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
    iento
    -0.08
     herk
    -0.07
    amespace
    -0.07
    atown
    -0.07
    ãĥ¼ãĥī
    -0.07
    ¢°
    -0.07
     øns
    -0.06
    amework
    -0.06
    tae
    -0.06
     ilet
    -0.06
    POSITIVE LOGITS
    ombat
    0.06
    r
    0.06
     smr
    0.06
    antan
    0.06
    Json
    0.06
    UF
    0.06
    sted
    0.06
     jer
    0.05
    upa
    0.05
    kur
    0.05
    Activations Density 0.023%

    No Known Activations