© 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. 15-LLAMASCOPE-RES-131K
    11. 87844
    Prev
    Next
    INDEX
    Explanations

    names and identities relevant to Islamic or historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Two or three letter sequences that represent country/organization domain codes or parts of international proper names, often appearing in digital contexts or references.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ils
    -0.08
    ond
    -0.07
    ellas
    -0.07
    ven
    -0.07
    xic
    -0.07
    IPH
    -0.06
    ArgumentException
    -0.06
    ajaran
    -0.06
    712
    -0.06
    ENAME
    -0.06
    POSITIVE LOGITS
    ognito
    0.08
    (Int
    0.07
    quierda
    0.07
    ãĥ¬ãĥĥãĥĪ
    0.07
    ónico
    0.07
    elong
    0.07
    annis
    0.07
    fulness
    0.07
    ÅĽÄĩ
    0.06
    便
    0.06
    Activations Density 0.122%

    No Known Activations