© 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. 128243
    Prev
    Next
    INDEX
    Explanations

    references to financial leadership roles or positions

    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
    cia
    -0.07
     Truman
    -0.07
    enstein
    -0.07
    ÂŃi
    -0.06
    ableObject
    -0.06
    Łèĥ½
    -0.06
    zend
    -0.06
    isku
    -0.06
    953
    -0.06
    ýš
    -0.06
    POSITIVE LOGITS
    UTTON
    0.07
    lo
    0.07
    ehr
    0.06
    á»ķ
    0.06
    \Factory
    0.06
    xDF
    0.06
    um
    0.06
    .Enum
    0.06
    _msgs
    0.06
    utton
    0.06
    Activations Density 0.000%

    No Known Activations