© 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. 15-LLAMASCOPE-RES-131K
    11. 61957
    Prev
    Next
    INDEX
    Explanations

    programming functions and their definitions

    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
    باÙĨ
    -0.07
    antry
    -0.06
    uhan
    -0.06
    AsString
    -0.06
     hawk
    -0.05
    og
    -0.05
    asaki
    -0.05
     Mobile
    -0.05
    ud
    -0.05
    ack
    -0.05
    POSITIVE LOGITS
    ndx
    0.08
    á»IJ
    0.07
    ETCH
    0.07
    ehr
    0.07
    ucci
    0.07
    VERR
    0.07
    nga
    0.07
     CreateTable
    0.07
    landers
    0.07
    Verdana
    0.07
    Activations Density 0.001%

    No Known Activations