© 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. 9-LLAMASCOPE-RES-131K
    11. 98404
    Prev
    Next
    INDEX
    Explanations

    titles of horror movies and their associated elements

    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
    Mono
    -0.06
    511
    -0.06
    zym
    -0.06
     Carl
    -0.06
    DRAM
    -0.06
    astos
    -0.06
     Mono
    -0.06
     beg
    -0.06
    apper
    -0.06
    mono
    -0.06
    POSITIVE LOGITS
    lez
    0.07
     cords
    0.07
    @show
    0.07
    .twitch
    0.07
    ULSE
    0.07
    arty
    0.06
    ensburg
    0.06
    abor
    0.06
    ìĭ
    0.06
    jab
    0.06
    Activations Density 0.007%

    No Known Activations