© 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. 15-LLAMASCOPE-RES-131K
    6. 27059
    Prev
    Next
    INDEX
    Explanations

    phrases indicating options or selections

    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
    jedn
    -0.08
    á»IJ
    -0.07
    ợi
    -0.07
    gregator
    -0.07
     jig
    -0.06
     itself
    -0.06
    ÙĬÙĪÙĨ
    -0.06
    ức
    -0.06
    voj
    -0.06
    oras
    -0.06
    POSITIVE LOGITS
     among
    0.07
     options
    0.07
     either
    0.07
     several
    0.07
    options
    0.07
    angel
    0.07
    among
    0.07
     choices
    0.07
    choices
    0.06
     amongst
    0.06
    Activations Density 0.003%

    No Known Activations