© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 40691
    Prev
    Next
    INDEX
    Explanations

    elements related to writing structure and coherence

    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
     Tune
    -0.07
    oggler
    -0.06
     phys
    -0.06
    в
    -0.06
    AVOR
    -0.06
     NIC
    -0.06
    PG
    -0.06
     Installation
    -0.06
    illet
    -0.06
    agem
    -0.06
    POSITIVE LOGITS
    ertas
    0.07
    elsing
    0.07
    -topic
    0.07
     kola
    0.07
     EXEMPLARY
    0.07
    -writing
    0.07
    crets
    0.07
     writing
    0.07
    Periph
    0.07
    ngen
    0.07
    Activations Density 0.002%

    No Known Activations