© 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. 70957
    Prev
    Next
    INDEX
    Explanations

    key details related to book attributes, such as author names, themes, and story elements

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

    Text that marks the transition between metadata or book information and the beginning of the actual narrative content, typically appearing at the end of book descriptions or promotional material before the story excerpt begins.

    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
     \`
    -0.09
    èĪĮ
    -0.08
    ALSE
    -0.08
    ylon
    -0.08
    ARED
    -0.08
    ilden
    -0.08
     ãģĿãģ®ä»ĸ
    -0.08
    ãģĿãģ®ä»ĸ
    -0.07
    engin
    -0.07
    spm
    -0.07
    POSITIVE LOGITS
     th
    0.07
     orphan
    0.07
    279
    0.06
     Mas
    0.06
    otime
    0.05
     prest
    0.05
     tour
    0.05
     
    0.05
    untu
    0.05
     Rating
    0.05
    Activations Density 0.019%

    No Known Activations