© 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. 40291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" as a preposition or conjunction

    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
     annonces
    -0.06
    stalk
    -0.06
    abbo
    -0.06
    ipur
    -0.06
    reste
    -0.06
    -esque
    -0.06
    amer
    -0.06
     iParam
    -0.06
    readcr
    -0.06
     figur
    -0.06
    POSITIVE LOGITS
    ozilla
    0.07
     villagers
    0.07
    abwe
    0.07
     bize
    0.07
    imd
    0.06
     girls
    0.06
    .tap
    0.06
    ynamo
    0.06
    erializer
    0.06
     Ekon
    0.06
    Activations Density 0.000%

    No Known Activations