© 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. 124241
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting or mathematical symbols often used in equations

    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
    Ãł
    -0.07
    s
    -0.07
    elpers
    -0.06
    idak
    -0.06
    lobal
    -0.06
    ãĥĥãĥĪ
    -0.06
    plx
    -0.06
    اÙħ
    -0.06
    urm
    -0.06
    olume
    -0.06
    POSITIVE LOGITS
    InSection
    0.07
    orget
    0.07
    ehr
    0.07
    èĪį
    0.06
    ाà¤Ĭ
    0.06
    Resizable
    0.06
    aling
    0.06
     INCIDENT
    0.06
    ãĥ©ãĤ¯
    0.06
    tod
    0.06
    Activations Density 0.065%

    No Known Activations