© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87967
    Prev
    Next
    INDEX
    Explanations

    references to statistical models and numerical data related to classifications

    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
     elsewhere
    -0.07
    thing
    -0.06
    ÑĤÑİ
    -0.06
    adden
    -0.06
     Marks
    -0.06
    THING
    -0.06
    .snapshot
    -0.06
    ailer
    -0.06
    etri
    -0.06
     boarding
    -0.05
    POSITIVE LOGITS
     each
    0.23
    each
    0.21
    Each
    0.18
     Each
    0.18
     кажд
    0.16
     EACH
    0.15
    .each
    0.15
     má»Ĺi
    0.15
     cada
    0.15
    æ¯ı
    0.15
    Activations Density 0.042%

    No Known Activations