© 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. 126902
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and patterns in written content

    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
    yp
    -0.06
    ames
    -0.06
     blocking
    -0.06
    มห
    -0.06
    egen
    -0.06
    zan
    -0.06
    avic
    -0.06
    erg
    -0.05
    esium
    -0.05
    ounds
    -0.05
    POSITIVE LOGITS
    /dc
    0.07
    PIP
    0.07
    830
    0.07
    Ä°Åŀ
    0.07
    ucher
    0.07
    aclass
    0.06
    399
    0.06
     اÙĦأس
    0.06
    ainless
    0.06
    421
    0.06
    Activations Density 0.001%

    No Known Activations