© 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. 106581
    Prev
    Next
    INDEX
    Explanations

    references to figures and illustrations in a technical document

    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
    ën
    -0.07
    vsp
    -0.07
    ter
    -0.05
    /library
    -0.05
    asso
    -0.05
    ová
    -0.05
    ass
    -0.05
    ongs
    -0.05
    har
    -0.05
    /by
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.10
    -relative
    0.07
    ezier
    0.07
    awe
    0.07
    stringLiteral
    0.07
    ụn
    0.07
    ıi
    0.07
     pregn
    0.07
    zsche
    0.07
    \OptionsResolver
    0.07
    Activations Density 0.008%

    No Known Activations