© 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. 104364
    Prev
    Next
    INDEX
    Explanations

    actions related to donation processes

    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
    reck
    -0.07
    burgh
    -0.07
    lopen
    -0.06
     Occupation
    -0.06
    pong
    -0.06
    loi
    -0.06
    leo
    -0.06
    UNK
    -0.06
     valleys
    -0.05
    .mapping
    -0.05
    POSITIVE LOGITS
     anonymously
    0.08
    çķĻ
    0.07
     çķĻ
    0.07
    anonymous
    0.07
    deposit
    0.07
     Swinger
    0.07
     deix
    0.07
    tempt
    0.07
     deposit
    0.07
     leaving
    0.07
    Activations Density 0.019%

    No Known Activations