© 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. 30149
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events related to geopolitical dynamics

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

    Function words (especially "as") that connect clauses providing contextual information about a person's role, relationship, or explanation for an action.

    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
    pta
    -0.07
    isky
    -0.07
    emey
    -0.07
     opat
    -0.06
    atos
    -0.06
     LIABILITY
    -0.06
    odb
    -0.06
    ÛĮدا
    -0.06
    Ñij
    -0.06
    olian
    -0.06
    POSITIVE LOGITS
    ä½ľä¸º
    0.11
    æ¯ķ
    0.09
     as
    0.09
     being
    0.08
     sebagai
    0.08
     jako
    0.07
     Ñıк
    0.07
     since
    0.07
     status
    0.06
     als
    0.06
    Activations Density 0.052%

    No Known Activations