© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77367
    Prev
    Next
    INDEX
    Explanations

    instances of statistics or data presentation regarding public health

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

    The text marks the end of a heading, title, or introductory statement that leads directly into a list, enumeration, or new content section. It typically appears at a transition point where the document switches from announcing a topic to presenting substantive information about that topic.

    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
    ustos
    -0.07
    cisi
    -0.07
     hous
    -0.06
     inval
    -0.06
     (*(
    -0.06
    ibus
    -0.06
    AYOUT
    -0.06
    ĥĿ
    -0.06
    aux
    -0.06
    adb
    -0.06
    POSITIVE LOGITS
    1
    0.09
     #
    0.09
    nev
    0.08
    yth
    0.07
    721
    0.07
     Ha
    0.07
    Ha
    0.07
    ï¼ij
    0.07
    01
    0.07
    ignon
    0.07
    Activations Density 0.033%

    No Known Activations