© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119110
    Prev
    Next
    INDEX
    Explanations

    mention of the name "Burton" and variations of it

    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
    सन
    -0.07
    alm
    -0.07
    esch
    -0.07
    ãģ¿
    -0.06
    enberg
    -0.06
    fold
    -0.06
    ernen
    -0.06
    /apis
    -0.06
    ose
    -0.06
    ads
    -0.06
    POSITIVE LOGITS
    riel
    0.08
    .scalablytyped
    0.08
    วล
    0.07
    \FrameworkBundle
    0.07
    quoise
    0.07
    geois
    0.07
    prung
    0.07
    MITTED
    0.07
    vant
    0.07
     Robbins
    0.06
    Activations Density 0.026%

    No Known Activations