© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28344
    Prev
    Next
    INDEX
    Explanations

    terms related to access control and privacy restrictions

    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
    СÐŀ
    -0.07
     corner
    -0.06
    /GL
    -0.06
    zin
    -0.06
    浩
    -0.06
    بر
    -0.06
    urch
    -0.06
    pliant
    -0.05
     Bracket
    -0.05
    artic
    -0.05
    POSITIVE LOGITS
     restricted
    0.14
     only
    0.12
     Restricted
    0.12
    restricted
    0.11
     restrict
    0.11
    Restricted
    0.11
     exclusive
    0.11
     exclus
    0.11
     private
    0.11
     ONLY
    0.10
    Activations Density 0.061%

    No Known Activations