© 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. 106440
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and categorization within various contexts

    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
    ihan
    -0.07
    å±±å¸Ĥ
    -0.07
    .timing
    -0.07
    ÑĢей
    -0.07
    oro
    -0.07
    çļĦåľ°æĸ¹
    -0.07
    urr
    -0.07
    ALIGN
    -0.07
    ervo
    -0.07
    /cms
    -0.07
    POSITIVE LOGITS
     ones
    0.19
     Ones
    0.12
     alike
    0.12
    ones
    0.10
    .ones
    0.08
     depending
    0.07
     others
    0.07
    ewise
    0.07
    ONES
    0.07
    )
    0.06
    Activations Density 0.040%

    No Known Activations