© 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. 106916
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly states and countries

    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
    ahan
    -0.07
    IDD
    -0.07
    éģł
    -0.07
    izza
    -0.06
    ç½
    -0.06
    idel
    -0.06
    axon
    -0.06
    izard
    -0.06
    ách
    -0.06
    anker
    -0.06
    POSITIVE LOGITS
    661
    0.07
     forControlEvents
    0.07
    agna
    0.06
    641
    0.06
    apia
    0.06
    ngör
    0.06
    تبÙĩ
    0.06
    0.06
     to
    0.06
    .defer
    0.06
    Activations Density 0.006%

    No Known Activations