© 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. 15-LLAMASCOPE-RES-131K
    11. 86774
    Prev
    Next
    INDEX
    Explanations

    titles and categories of television shows

    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
    μί
    -0.08
    arf
    -0.07
     radioButton
    -0.06
     Reich
    -0.06
    commission
    -0.06
    à¤Ĥव
    -0.06
    çĽĸ
    -0.06
     íı
    -0.06
    EMPL
    -0.06
    /license
    -0.06
    POSITIVE LOGITS
    icter
    0.06
     çī
    0.06
     titles
    0.06
    ngr
    0.06
    igs
    0.06
    adro
    0.06
    cido
    0.06
    Titles
    0.06
     scores
    0.06
     aka
    0.06
    Activations Density 0.003%

    No Known Activations