© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3613
    Prev
    Next
    INDEX
    Explanations

    titles of well-known movies

    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
     alma
    -0.07
    anca
    -0.06
     Giang
    -0.06
     Surre
    -0.06
    поÑģ
    -0.06
    consume
    -0.06
    eps
    -0.06
    alc
    -0.06
    anela
    -0.06
     defeated
    -0.06
    POSITIVE LOGITS
    _inches
    0.07
     expend
    0.06
     movie
    0.06
    ุย
    0.06
    .decoder
    0.06
    ãģĻãģĻ
    0.06
    ìī
    0.06
    çĽ£çĿ£
    0.06
     numberWith
    0.06
    ÐĴÑĸн
    0.06
    Activations Density 0.092%

    No Known Activations