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. 96281
    Prev
    Next
    INDEX
    Explanations

    proper nouns and individuals mentioned in political contexts

    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
    æ°¸ä¹ħ
    -0.07
    /fw
    -0.06
    oog
    -0.06
    ãĤĬãģ¨
    -0.06
    lobals
    -0.06
     Orn
    -0.06
    lette
    -0.06
    à¤łà¤¨
    -0.06
     fractional
    -0.06
    áºŃp
    -0.06
    POSITIVE LOGITS
    ouve
    0.07
    anton
    0.07
    üns
    0.06
    kers
    0.06
    aket
    0.06
    anka
    0.06
     Consort
    0.06
    ouz
    0.06
    лаж
    0.06
    coli
    0.06
    Activations Density 0.017%

    No Known Activations