© 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. 9-LLAMASCOPE-RES-131K
    11. 97135
    Prev
    Next
    INDEX
    Explanations

    elements of contact information and application instructions

    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
    ango
    -0.08
    ible
    -0.06
    rey
    -0.06
    peÄį
    -0.06
    ÑĤап
    -0.06
    Lifecycle
    -0.06
    phin
    -0.06
     ÐĽÐ¸
    -0.06
     hab
    -0.06
    638
    -0.06
    POSITIVE LOGITS
    carrier
    0.07
    autor
    0.06
    OME
    0.06
    URITY
    0.06
    chez
    0.06
    碼
    0.06
    zd
    0.06
     duty
    0.06
    oog
    0.06
     uÄŁ
    0.06
    Activations Density 0.025%

    No Known Activations