© 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. 9-LLAMASCOPE-RES-131K
    11. 95771
    Prev
    Next
    INDEX
    Explanations

    lines of code indicating the end of conditional compilation

    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
    assen
    -0.06
    anik
    -0.06
    ater
    -0.06
    µ¬
    -0.06
     Sem
    -0.05
    mont
    -0.05
    临
    -0.05
    per
    -0.05
    comm
    -0.05
    bol
    -0.05
    POSITIVE LOGITS
    -begin
    0.08
    Å¡tÃŃ
    0.08
    amus
    0.07
    umblr
    0.07
    idla
    0.07
    oproject
    0.07
    FFE
    0.07
    rack
    0.07
    icers
    0.07
    LOCKS
    0.07
    Activations Density 0.035%

    No Known Activations