© 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. 40723
    Prev
    Next
    INDEX
    Explanations

    elements related to regulatory conditions and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ilib
    -0.07
    Ïİνα
    -0.07
    WXYZ
    -0.07
    esiz
    -0.07
    agic
    -0.06
    .Sdk
    -0.06
    positor
    -0.06
     migrationBuilder
    -0.06
     mappedBy
    -0.06
    WND
    -0.06
    POSITIVE LOGITS
     shall
    0.08
    ded
    0.07
     Shall
    0.07
    fect
    0.06
     SHALL
    0.06
     neod
    0.06
     satisfactory
    0.06
    _timing
    0.06
    á»Ļc
    0.06
    ẻ
    0.06
    Activations Density 0.004%

    No Known Activations