© 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. 27560
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "string" and its variants in programming contexts

    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
    fov
    -0.08
    odyn
    -0.07
    fos
    -0.07
    umbs
    -0.07
    paid
    -0.07
    ibal
    -0.07
    POCH
    -0.06
    blick
    -0.06
    onal
    -0.06
    ingles
    -0.06
    POSITIVE LOGITS
    EDIA
    0.06
    ëĵĿ
    0.06
     æ¯
    0.06
    lish
    0.06
    ê·ľ
    0.06
    -Ta
    0.06
     predictive
    0.06
    _literals
    0.05
    extras
    0.05
    ¥
    0.05
    Activations Density 0.003%

    No Known Activations