© 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. 125880
    Prev
    Next
    INDEX
    Explanations

    null values or references in code

    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
    le
    -0.07
    als
    -0.06
    :
    -0.06
    cp
    -0.06
     m
    -0.06
     Conspiracy
    -0.05
    lep
    -0.05
    -a
    -0.05
    rens
    -0.05
     Carroll
    -0.05
    POSITIVE LOGITS
    Charsets
    0.09
    istrovstvÃŃ
    0.08
    872
    0.08
    ãİ
    0.07
    DataTask
    0.07
    WindowTitle
    0.07
    agua
    0.07
    æ³³
    0.07
    ">ÃĹ</
    0.07
    jde
    0.07
    Activations Density 0.008%

    No Known Activations