© 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. 1170
    Prev
    Next
    INDEX
    Explanations

    questions that seek validation or approval

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

    Answer/response indicators that appear immediately after a question, often in conversational or Q&A text formats.

    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
    oystick
    -0.07
    alian
    -0.06
    ocab
    -0.06
     Bliss
    -0.06
    col
    -0.06
     CHARSET
    -0.06
    nul
    -0.06
    icies
    -0.06
    ób
    -0.06
    _OVERRIDE
    -0.06
    POSITIVE LOGITS
     yes
    0.25
     YES
    0.24
     Yes
    0.23
    YES
    0.21
    yes
    0.20
    Yes
    0.20
    _yes
    0.16
    =yes
    0.16
    "Yes
    0.16
    _YES
    0.15
    Activations Density 0.131%

    No Known Activations