© 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. 17-LLAMASCOPE-RES-131K
    11. 124904
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or duration

    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
    elight
    -0.07
    bose
    -0.06
    asi
    -0.06
     Kraj
    -0.06
    iên
    -0.06
    iza
    -0.06
    uming
    -0.06
    plr
    -0.06
    apper
    -0.06
    esel
    -0.06
    POSITIVE LOGITS
    дÑĥ
    0.07
    phin
    0.06
    times
    0.06
    evin
    0.06
    RestController
    0.06
    Du
    0.06
    igham
    0.06
    thon
    0.06
    .spark
    0.06
    780
    0.06
    Activations Density 0.019%

    No Known Activations