© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18106
    Prev
    Next
    INDEX
    Explanations

    instances of the word "different" and its variants, as well as references to exceptions and exemptions

    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
    kup
    -0.08
    ÑĢовод
    -0.07
    emoc
    -0.07
    zap
    -0.07
    inz
    -0.07
    ön
    -0.07
    uplic
    -0.07
    á»Ń
    -0.07
    acier
    -0.07
    ograph
    -0.07
    POSITIVE LOGITS
     except
    0.09
    except
    0.08
    olicy
    0.06
    krát
    0.06
    _except
    0.06
     Except
    0.06
    aida
    0.06
    ewith
    0.06
     activeClassName
    0.06
    arily
    0.06
    Activations Density 0.002%

    No Known Activations