Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96174
    Prev
    Next
    INDEX
    Explanations

    names of prominent political figures

    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
    unga
    -0.07
    asar
    -0.07
    еÑĢк
    -0.06
    ync
    -0.06
     Canton
    -0.06
    OMEM
    -0.06
    coach
    -0.06
    stamp
    -0.06
    Stamp
    -0.06
     cir
    -0.06
    POSITIVE LOGITS
    atak
    0.07
    raid
    0.07
     ///</
    0.07
    iku
    0.07
    lobber
    0.06
     addCriterion
    0.06
    ices
    0.06
    skins
    0.06
     GridLayout
    0.06
    WSC
    0.06
    Activations Density 0.000%

    No Known Activations