© 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. 2483
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding and programming challenges

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

    The colon followed by a space after the letter "A", indicating a question-answer format in forum or discussion posts where "A:" indicates the start of an answer.

    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
    jing
    -0.08
    iland
    -0.07
    ÚĺÛĮ
    -0.07
    gon
    -0.07
    ilia
    -0.07
    ç·ł
    -0.07
    ERO
    -0.07
    人人
    -0.07
    λλι
    -0.07
    ÏĦιο
    -0.07
    POSITIVE LOGITS
     equival
    0.06
    ckett
    0.06
    Ãł
    0.06
    akis
    0.05
    %E
    0.05
     ways
    0.05
     Cust
    0.05
    ãĥĸãĥŃ
    0.05
    cket
    0.05
    atal
    0.05
    Activations Density 0.015%

    No Known Activations