© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76003
    Prev
    Next
    INDEX
    Explanations

    the phrase "anyone who," indicating references to people and their characteristics or actions

    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
    yro
    -0.06
    alu
    -0.06
    eah
    -0.05
    irim
    -0.05
    rames
    -0.05
     Turnbull
    -0.05
    eb
    -0.05
    OOM
    -0.05
    udge
    -0.05
     none
    -0.05
    POSITIVE LOGITS
    -any
    0.10
     anytime
    0.08
     Anyone
    0.08
    Any
    0.08
     Any
    0.08
     who
    0.08
     anyone
    0.08
    (any
    0.08
    orton
    0.07
    Anyone
    0.07
    Activations Density 0.005%

    No Known Activations