© 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. 124061
    Prev
    Next
    INDEX
    Explanations

    references to videos and watching content

    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
    askets
    -0.07
    idget
    -0.07
     Aviv
    -0.07
    echan
    -0.07
    verity
    -0.06
    ãĥªãĤ«
    -0.06
    eÅŁ
    -0.06
     Viewer
    -0.06
    erties
    -0.06
    partition
    -0.06
    POSITIVE LOGITS
     video
    0.07
    ?v
    0.07
     interview
    0.07
    üs
    0.06
    iness
    0.06
    abe
    0.06
    bul
    0.06
    levator
    0.06
    ed
    0.06
     below
    0.06
    Activations Density 0.007%

    No Known Activations