© 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. 15-LLAMASCOPE-RES-131K
    11. 103569
    Prev
    Next
    INDEX
    Explanations

    HTML comment or markup fragments

    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
    antu
    -0.09
    acula
    -0.07
    izza
    -0.07
    trand
    -0.07
    nea
    -0.07
    äch
    -0.06
    cken
    -0.06
    mono
    -0.06
    anh
    -0.06
    EMA
    -0.06
    POSITIVE LOGITS
    ÏĦί
    0.06
    nou
    0.06
     vÃŃde
    0.06
    _MAGIC
    0.06
     dilation
    0.06
    álo
    0.06
    Dean
    0.06
    ETO
    0.06
     rigid
    0.06
    CTL
    0.06
    Activations Density 0.000%

    No Known Activations