© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129140
    Prev
    Next
    INDEX
    Explanations

    instructions related to managing clipboard functions

    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
    زÙĪ
    -0.08
    /Dk
    -0.08
     <!--[
    -0.07
    FRING
    -0.07
    ember
    -0.07
     Relay
    -0.07
    ider
    -0.07
    @Setter
    -0.07
    oundary
    -0.07
    rets
    -0.07
    POSITIVE LOGITS
    uell
    0.06
    .Delete
    0.06
     move
    0.06
     delete
    0.06
     edit
    0.06
    AME
    0.06
    sort
    0.06
     bulk
    0.06
    unittest
    0.06
     editing
    0.06
    Activations Density 0.010%

    No Known Activations