Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128822
    Prev
    Next
    INDEX
    Explanations

    references to avant-garde art and its influences

    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
     corpor
    -0.06
     Dump
    -0.06
    anja
    -0.06
    unya
    -0.06
     annex
    -0.06
    _ghost
    -0.06
    usting
    -0.06
    вед
    -0.06
    lang
    -0.06
     Annex
    -0.06
    POSITIVE LOGITS
    sonian
    0.08
    deaux
    0.07
    .usermodel
    0.07
    UrlParser
    0.07
    Lite
    0.07
    LObject
    0.07
    ácil
    0.07
    phere
    0.06
     limburg
    0.06
    cassert
    0.06
    Activations Density 0.023%

    No Known Activations