© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28789
    Prev
    Next
    INDEX
    Explanations

    mentions of Melania Trump

    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
    eba
    -0.06
    ptal
    -0.06
     Hastings
    -0.06
    sen
    -0.06
    ;amp
    -0.06
    aeda
    -0.06
    unts
    -0.06
    ees
    -0.06
     Bis
    -0.06
    semblies
    -0.06
    POSITIVE LOGITS
    illance
    0.07
    .gov
    0.07
     Consort
    0.07
     consort
    0.07
     Mrs
    0.07
    BOSE
    0.06
    emet
    0.06
    Mrs
    0.06
     Residence
    0.06
    ollen
    0.06
    Activations Density 0.011%

    No Known Activations