© 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. 117970
    Prev
    Next
    INDEX
    Explanations

    terms indicating categories or classifications related to collections or groupings

    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
    æħ
    -0.06
    arent
    -0.05
     svc
    -0.05
    /qu
    -0.05
     frustr
    -0.05
     Lambert
    -0.05
    gom
    -0.05
    -mon
    -0.05
     Advertisement
    -0.05
    idge
    -0.05
    POSITIVE LOGITS
    ëĮ
    0.07
    aggio
    0.07
    SURE
    0.07
    avou
    0.07
    rán
    0.07
    odia
    0.07
    erras
    0.07
    å°¼äºļ
    0.07
    ideographic
    0.07
    еÑĢк
    0.07
    Activations Density 0.000%

    No Known Activations