© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16266
    Prev
    Next
    INDEX
    Explanations

    references to professional roles or occupations in a collaborative context

    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
    asz
    -0.07
    .setTo
    -0.07
     klu
    -0.06
    azole
    -0.06
    oux
    -0.06
    asma
    -0.06
     seksi
    -0.06
    allback
    -0.06
    allen
    -0.06
    idis
    -0.06
    POSITIVE LOGITS
     representatives
    0.09
     invited
    0.07
     together
    0.07
    840
    0.07
    ixer
    0.07
    oload
    0.06
     discuss
    0.06
     invite
    0.06
    732
    0.06
     representative
    0.06
    Activations Density 0.027%

    No Known Activations