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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11423
    Prev
    Next
    INDEX
    Explanations

    lexical variations or inflections of the word "so"

    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
     weiber
    -0.07
    _DECLARE
    -0.07
    587
    -0.07
    aits
    -0.07
     geschichten
    -0.07
    ocs
    -0.06
    bable
    -0.06
     pornofilm
    -0.06
    ÃŃf
    -0.06
    MUX
    -0.06
    POSITIVE LOGITS
    som
    0.15
    dan
    0.15
    dana
    0.15
    led
    0.12
    ng
    0.11
    ngen
    0.11
    nger
    0.10
    v
    0.10
    vida
    0.10
    ngle
    0.10
    Activations Density 0.003%

    No Known Activations