© 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. 18388
    Prev
    Next
    INDEX
    Explanations

    definitions or descriptions of techniques or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phrases containing linking verbs that define or characterize what something is or isn't, often providing clarification about the nature or purpose of the subject.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     syn
    -0.06
    ores
    -0.06
     Pare
    -0.06
    isset
    -0.06
     vit
    -0.05
    çİī
    -0.05
    deo
    -0.05
     Protection
    -0.05
    веÑĤ
    -0.05
    andon
    -0.05
    POSITIVE LOGITS
     intended
    0.14
     meant
    0.12
     designed
    0.09
     purpose
    0.09
     пÑĢизнаÑĩ
    0.09
     neither
    0.08
     intend
    0.08
    缮çļĦ
    0.08
    Designed
    0.08
     intent
    0.08
    Activations Density 0.047%

    No Known Activations