© 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. 18359
    Prev
    Next
    INDEX
    Explanations

    phrases that involve summarization or description in various contexts

    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
    stk
    -0.07
    ervo
    -0.06
     zase
    -0.06
    ÙĤرار
    -0.06
    [char
    -0.06
    ownik
    -0.06
    ">ÃĹ</
    -0.06
    że
    -0.06
    Tri
    -0.06
    ILI
    -0.06
    POSITIVE LOGITS
     single
    0.16
    single
    0.12
     SINGLE
    0.12
     Single
    0.11
     simple
    0.10
    -single
    0.10
     nutshell
    0.10
    Single
    0.10
    (single
    0.10
    /single
    0.10
    Activations Density 0.093%

    No Known Activations