© 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. 79939
    Prev
    Next
    INDEX
    Explanations

    prepositions related to specific spatial or contextual relationships

    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
    _malloc
    -0.07
    ãĥĪãĥª
    -0.07
    rak
    -0.07
    acker
    -0.07
     draining
    -0.07
    ozor
    -0.06
    puted
    -0.06
    ester
    -0.06
    _SPI
    -0.06
    madıģı
    -0.06
    POSITIVE LOGITS
     Goldberg
    0.07
    οκ
    0.06
    oleon
    0.06
    bery
    0.06
     Halk
    0.06
    yat
    0.06
     case
    0.06
    'options
    0.06
    older
    0.05
    zes
    0.05
    Activations Density 0.041%

    No Known Activations