© 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. 16306
    Prev
    Next
    INDEX
    Explanations

    quotations or dialogue marks in text

    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
     ÙĥÙĨت
    -0.07
    ć
    -0.07
    еÑĩ
    -0.06
     Hurt
    -0.06
    ă
    -0.06
    è¿Ļä¸Ģ
    -0.06
    643
    -0.06
    lage
    -0.06
    à¥įरत
    -0.06
    avad
    -0.06
    POSITIVE LOGITS
    strup
    0.07
    ETER
    0.07
    iox
    0.07
    antasy
    0.07
    ombs
    0.06
    nici
    0.06
    imers
    0.06
    Å¡ov
    0.06
    ventario
    0.06
    ioni
    0.06
    Activations Density 0.000%

    No Known Activations