© 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. 119320
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making entities or autonomous agents

    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
    DSA
    -0.07
     -
    -0.07
    YL
    -0.07
     aforementioned
    -0.07
    astically
    -0.06
    peare
    -0.06
    ocate
    -0.06
    unpack
    -0.06
    rchive
    -0.06
     –
    -0.06
    POSITIVE LOGITS
    è³ŀ
    0.06
    ars
    0.06
    á»ķ
    0.06
     muschi
    0.06
     ramp
    0.06
    ãĥ¼ãĥĩ
    0.06
     Hut
    0.06
    ÑĢавилÑĮ
    0.06
    043
    0.06
    UCKET
    0.06
    Activations Density 0.000%

    No Known Activations