© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27001
    Prev
    Next
    INDEX
    Explanations

    instances of question and answer formats

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

    The token ":" or "." following the letter "A" at the beginning of an answer in a question-and-answer format, often occurring at the start of a new paragraph after a question.

    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
     Esp
    -0.06
    orca
    -0.06
    -tm
    -0.06
    )?$
    -0.06
    ije
    -0.05
    azzo
    -0.05
     Inspiration
    -0.05
     Sher
    -0.05
    inc
    -0.05
    ooter
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.09
    asal
    0.07
    028
    0.07
    IGIN
    0.07
    nev
    0.07
    ãģĿãĤĮãģ¯
    0.07
    ìĹŃ
    0.07
    оÑī
    0.07
    .getAs
    0.06
    fixture
    0.06
    Activations Density 0.007%

    No Known Activations