© 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. 22-LLAMASCOPE-RES-131K
    11. 3591
    Prev
    Next
    INDEX
    Explanations

    references to integration and transformation processes in various contexts

    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
    amins
    -0.08
     lui
    -0.07
    ingroup
    -0.07
    á»ĵn
    -0.07
     him
    -0.07
    _planes
    -0.07
    imson
    -0.06
     moż
    -0.06
    /tty
    -0.06
    him
    -0.06
    POSITIVE LOGITS
     peoples
    0.21
     someone
    0.20
    人们
    0.18
     everyone
    0.18
     somebody
    0.18
     people
    0.17
     anyone
    0.16
     everybody
    0.16
    someone
    0.16
    人çļĦ
    0.16
    Activations Density 0.375%

    No Known Activations