© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126467
    Prev
    Next
    INDEX
    Explanations

    terms related to rigidity and shape in a mathematical context

    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
    raya
    -0.08
    argin
    -0.07
    ıs
    -0.06
    ertia
    -0.06
    _slope
    -0.06
     spin
    -0.06
    loid
    -0.06
    äs
    -0.06
    коз
    -0.06
    LOCK
    -0.06
    POSITIVE LOGITS
    ết
    0.07
    elist
    0.06
     Crown
    0.06
    ogle
    0.06
    quires
    0.06
    dire
    0.06
     crown
    0.06
    #echo
    0.06
    annya
    0.06
    ularity
    0.06
    Activations Density 0.039%

    No Known Activations