© 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. 126196
    Prev
    Next
    INDEX
    Explanations

    phrases expressing similarity or comparisons

    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
    Ñİк
    -0.08
    каÑģ
    -0.07
    xfff
    -0.07
    edir
    -0.07
    yla
    -0.07
    phem
    -0.07
    IGHL
    -0.07
    åªĴ
    -0.07
    FG
    -0.07
    olan
    -0.07
    POSITIVE LOGITS
    other
    0.06
     closely
    0.06
    endl
    0.06
     crap
    0.06
     a
    0.06
    older
    0.06
    ãĤ¶
    0.06
     Bell
    0.06
     traditional
    0.05
     classic
    0.05
    Activations Density 0.015%

    No Known Activations