© 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. 128689
    Prev
    Next
    INDEX
    Explanations

    numerical or coded information, likely related to identification or categorization data

    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
    ebek
    -0.07
    ucch
    -0.06
    ernes
    -0.06
    üml
    -0.06
    sst
    -0.06
    /her
    -0.06
     Slack
    -0.06
    eview
    -0.06
     Verm
    -0.06
    ijkl
    -0.06
    POSITIVE LOGITS
    ovich
    0.07
    thora
    0.07
    пÑĢа
    0.07
    utow
    0.06
    _procs
    0.06
    нод
    0.06
    à¹Ĥร
    0.06
    emas
    0.06
    ENA
    0.06
    ìĪł
    0.06
    Activations Density 0.015%

    No Known Activations