© 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. 105906
    Prev
    Next
    INDEX
    Explanations

    terms related to visibility and transparency in social or political 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
    icerca
    -0.07
     Yam
    -0.07
    itor
    -0.06
    odian
    -0.06
    rám
    -0.06
    oki
    -0.06
    hood
    -0.06
    enic
    -0.06
     ance
    -0.06
    ToProps
    -0.06
    POSITIVE LOGITS
    aking
    0.07
    ëĭ¤ë©´
    0.07
    ues
    0.07
    TERS
    0.07
    ear
    0.06
     Besch
    0.06
    ettel
    0.06
    à¥įध
    0.06
    neath
    0.06
    ixo
    0.06
    Activations Density 0.005%

    No Known Activations