© 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. 17-LLAMASCOPE-RES-131K
    11. 60605
    Prev
    Next
    INDEX
    Explanations

    words that describe uniqueness and diversity in individuals, behaviors, or styles

    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
    lahoma
    -0.06
    /list
    -0.06
    ');?>"
    -0.06
    ee
    -0.06
    seud
    -0.06
     Carson
    -0.06
    stead
    -0.06
    浦
    -0.06
    /check
    -0.06
    idth
    -0.06
    POSITIVE LOGITS
    ities
    0.12
    ity
    0.09
    ALLY
    0.09
    ITIES
    0.08
    /random
    0.08
    /ext
    0.08
    eti
    0.08
    ally
    0.08
    itti
    0.08
    idade
    0.07
    Activations Density 0.008%

    No Known Activations