© 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. 22-LLAMASCOPE-RES-131K
    11. 4152
    Prev
    Next
    INDEX
    Explanations

    references to decisions, announcements, and claims made by individuals or organizations

    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
    .CopyTo
    -0.07
    ntax
    -0.07
    elez
    -0.07
    RLF
    -0.07
    umba
    -0.07
    enderit
    -0.07
    κÎŃ
    -0.07
     cumshot
    -0.07
    agra
    -0.06
    $MESS
    -0.06
    POSITIVE LOGITS
     retract
    0.19
     withdraw
    0.17
     resc
    0.17
     withdrawal
    0.16
     withdrawn
    0.16
    æĴ¤
    0.15
     withdrew
    0.15
     withdrawing
    0.15
     Withdraw
    0.14
    withdraw
    0.14
    Activations Density 0.107%

    No Known Activations