© 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. 14962
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or statuses that indicate success or completion

    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
    eniz
    -0.09
    ož
    -0.08
    jsonp
    -0.08
    ifton
    -0.08
    loub
    -0.08
    UNUSED
    -0.08
    iddi
    -0.08
     Ãĸn
    -0.08
    rens
    -0.07
    indh
    -0.07
    POSITIVE LOGITS
     anymore
    0.12
     nor
    0.10
     yet
    0.09
     due
    0.09
    nor
    0.08
    yet
    0.07
    due
    0.07
     because
    0.07
     Yet
    0.06
     بسبب
    0.06
    Activations Density 0.082%

    No Known Activations