© 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 EvalsExportsAPI 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. 106573
    Prev
    Next
    INDEX
    Explanations

    phrases and quotes that imply a perspective or opinion

    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
    ses
    -0.07
    inç
    -0.07
    aklı
    -0.07
    iner
    -0.06
    PLAIN
    -0.06
    #ad
    -0.06
    .peer
    -0.06
     pronto
    -0.06
    REGION
    -0.06
    ikal
    -0.06
    POSITIVE LOGITS
    ÂĿ
    0.10
    ething
    0.07
    istrovstvÃŃ
    0.07
    quot
    0.06
    abant
    0.06
     cellpadding
    0.06
    hots
    0.06
    ollapsed
    0.06
    -Regular
    0.06
    atten
    0.06
    Activations Density 0.030%

    No Known Activations