© 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. 56246
    Prev
    Next
    INDEX
    Explanations

    terms related to approval processes and comments

    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
    _certificate
    -0.06
    alker
    -0.06
    acam
    -0.06
     canh
    -0.06
    tsky
    -0.06
    ubar
    -0.06
    ãģ¨ãģį
    -0.06
    MethodImpl
    -0.06
    UTION
    -0.06
    974
    -0.06
    POSITIVE LOGITS
     approval
    0.19
     Approval
    0.16
     approve
    0.16
    approval
    0.15
     approvals
    0.14
     approved
    0.13
     approves
    0.12
    Approval
    0.12
     approving
    0.11
    approve
    0.11
    Activations Density 0.073%

    No Known Activations