© 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. 87275
    Prev
    Next
    INDEX
    Explanations

    statements that reflect complex reasoning and the evaluation of beliefs or evidence related to moral and social issues

    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
    .hu
    -0.08
    itchens
    -0.08
    allen
    -0.08
    _detach
    -0.07
    lingen
    -0.07
     ÑĩиÑģлÑĸ
    -0.07
     zel
    -0.07
    uos
    -0.07
    OffsetTable
    -0.07
    ESA
    -0.07
    POSITIVE LOGITS
     necessarily
    0.15
     automatically
    0.11
     anymore
    0.10
    ecessarily
    0.09
     or
    0.09
     therefore
    0.08
     immediately
    0.08
     Automatically
    0.08
     nor
    0.08
     thereby
    0.07
    Activations Density 0.032%

    No Known Activations