© 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. 3615
    Prev
    Next
    INDEX
    Explanations

    verbs associated with community assistance and support activities

    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
    /problem
    -0.08
    ãĥ¼ãĤ¯
    -0.07
    ãĥ¼ãĥ«ãĥī
    -0.06
    oret
    -0.06
     metic
    -0.06
    ve
    -0.06
    ActionTypes
    -0.06
    _Meta
    -0.06
    reet
    -0.06
     Ù¾ÛĮÚĨ
    -0.06
    POSITIVE LOGITS
    heimer
    0.07
     âĵĺ
    0.07
    leton
    0.06
    Spacer
    0.06
    heim
    0.06
    kowski
    0.06
    emann
    0.06
    Za
    0.06
     Fir
    0.06
    983
    0.06
    Activations Density 0.032%

    No Known Activations