© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126989
    Prev
    Next
    INDEX
    Explanations

    expressions of alternate names or aliases

    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
    eria
    -0.07
    ogle
    -0.07
    ohana
    -0.06
    ortic
    -0.06
    oodles
    -0.06
    ystate
    -0.06
    (disposing
    -0.06
    ÑĢап
    -0.06
    QUI
    -0.06
    lak
    -0.06
    POSITIVE LOGITS
    arme
    0.06
    ely
    0.06
     another
    0.06
    EFR
    0.06
    à¥ģà¤Ń
    0.06
    è³¢
    0.06
    antly
    0.05
    /stretch
    0.05
    ακ
    0.05
    aly
    0.05
    Activations Density 0.036%

    No Known Activations