© 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. 75254
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Nathan."

    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
    гоÑĤ
    -0.08
    ends
    -0.07
    resident
    -0.07
    reta
    -0.07
    agi
    -0.07
    dit
    -0.07
    hit
    -0.06
    neh
    -0.06
    vida
    -0.06
    amente
    -0.06
    POSITIVE LOGITS
    ouse
    0.09
    alysis
    0.07
    istic
    0.07
    urst
    0.07
    ial
    0.07
     Cir
    0.07
    645
    0.07
    ese
    0.06
    ilde
    0.06
    wick
    0.06
    Activations Density 0.004%

    No Known Activations