© 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. 5-LLAMASCOPE-RES-131K
    11. 126508
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals, particularly those related to entertainment or celebrity 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
    eload
    -0.07
    ordo
    -0.07
    .imgur
    -0.06
    rana
    -0.06
    eton
    -0.06
    opo
    -0.06
    opr
    -0.06
    ton
    -0.06
    ordan
    -0.06
     dust
    -0.06
    POSITIVE LOGITS
     Paz
    0.07
    оÑħ
    0.06
    sol
    0.06
    جا
    0.06
     اÙĦاÙĨ
    0.06
     ÑħоÑĩа
    0.06
    iguous
    0.06
    á»iji
    0.06
    Security
    0.06
    olin
    0.06
    Activations Density 0.032%

    No Known Activations