© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108119
    Prev
    Next
    INDEX
    Explanations

    suggestions and recommendations related to planning and decision-making, often in a social context

    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
    elines
    -0.07
    igo
    -0.06
    _continue
    -0.06
    ži
    -0.06
    anic
    -0.05
    anos
    -0.05
    angen
    -0.05
    -doc
    -0.05
    ipl
    -0.05
     Dash
    -0.05
    POSITIVE LOGITS
     hopefully
    0.10
     hãy
    0.08
     Hopefully
    0.08
    Hopefully
    0.08
    hopefully
    0.07
    /ng
    0.07
     remember
    0.07
    empl
    0.07
    INES
    0.06
    zimmer
    0.06
    Activations Density 0.015%

    No Known Activations