© 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. 120512
    Prev
    Next
    INDEX
    Explanations

    sequences of alphanumeric characters, likely related to IDs or codes

    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
    baugh
    -0.08
    eson
    -0.08
    icher
    -0.07
    swick
    -0.07
    ceso
    -0.07
    ebi
    -0.07
    OPSIS
    -0.06
    ÏĦεÏį
    -0.06
    ØŃÙĬ
    -0.06
    360
    -0.06
    POSITIVE LOGITS
     etc
    0.09
    etc
    0.07
    .UUID
    0.07
     uns
    0.06
     Mash
    0.06
    ioneer
    0.06
    uuid
    0.06
     Mane
    0.06
     Loved
    0.06
     blah
    0.06
    Activations Density 0.015%

    No Known Activations