© 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. 106113
    Prev
    Next
    INDEX
    Explanations

    references to Italy and Italian identity

    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
    peater
    -0.08
    avou
    -0.07
    DAC
    -0.07
    ç¼ĺ
    -0.07
    edly
    -0.07
    wig
    -0.07
    ved
    -0.06
    edReader
    -0.06
     kå
    -0.06
    ½Ķ
    -0.06
    POSITIVE LOGITS
     latter
    0.09
    zzo
    0.08
    bbe
    0.08
    abyrinth
    0.08
    -speaking
    0.07
    boro
    0.07
    agn
    0.07
    -American
    0.07
    gnore
    0.07
    ernal
    0.07
    Activations Density 0.013%

    No Known Activations