© 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. 15-LLAMASCOPE-RES-131K
    6. 61882
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related content

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

    A period or other punctuation mark at the end of a documentation block, code comment, or completed text segment, often followed by a closing quotation mark, code block delimiter, or new paragraph.

    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
    ä¾ĭå¦Ĥ
    -0.08
    ï¼Įå¦Ĥ
    -0.08
     e
    -0.07
    eg
    -0.07
    TRL
    -0.07
     напÑĢимеÑĢ
    -0.06
     eg
    -0.06
    جÙĨ
    -0.06
    _phys
    -0.06
    åĥıæĺ¯
    -0.06
    POSITIVE LOGITS
    adık
    0.07
     Notice
    0.07
    abei
    0.07
    notice
    0.07
    conti
    0.07
    QUENCE
    0.07
    ERRU
    0.07
     notice
    0.07
    Notice
    0.07
    azzo
    0.07
    Activations Density 0.033%

    No Known Activations