© 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. 119109
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or comparisons between entities

    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
    anja
    -0.07
    bern
    -0.07
    unting
    -0.06
    éĤ¦
    -0.06
     moo
    -0.06
    igger
    -0.06
    íݸ
    -0.06
    efe
    -0.06
    uner
    -0.06
    Dragging
    -0.06
    POSITIVE LOGITS
    _lifetime
    0.07
    yonel
    0.07
     exactly
    0.07
     far
    0.07
    á»ĭch
    0.07
    HQ
    0.07
     certainly
    0.06
     just
    0.06
    izik
    0.06
    asInstanceOf
    0.06
    Activations Density 0.031%

    No Known Activations