© 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 EvalsExportsinterp-engineNEWAPI 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. 86653
    Prev
    Next
    INDEX
    Explanations

    mentions of measurements or recommendations regarding safety and regulations

    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
    jian
    -0.07
    eum
    -0.07
    940
    -0.06
    Folders
    -0.06
     æ¼
    -0.06
    ÌĨ
    -0.06
    _Att
    -0.06
    .lt
    -0.06
    PWM
    -0.06
     enim
    -0.06
    POSITIVE LOGITS
    fal
    0.07
    apollo
    0.06
    ellular
    0.06
     fal
    0.06
    emy
    0.06
    ialis
    0.06
    ame
    0.06
    amina
    0.06
    herits
    0.06
    aper
    0.06
    Activations Density 0.026%

    No Known Activations