© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118061
    Prev
    Next
    INDEX
    Explanations

    documentation comments in code

    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
    isque
    -0.08
    alue
    -0.07
    483
    -0.07
    INCLUDING
    -0.07
    تاÙĨ
    -0.07
    enger
    -0.07
    IMS
    -0.07
    à¤ķरण
    -0.07
    輪
    -0.07
    ootball
    -0.07
    POSITIVE LOGITS
     Barber
    0.06
     getActivity
    0.06
    aked
    0.05
    itom
    0.05
     setResult
    0.05
    antor
    0.05
    oe
    0.05
     oe
    0.05
    era
    0.05
    -
    0.05
    Activations Density 0.000%

    No Known Activations