© 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. 76662
    Prev
    Next
    INDEX
    Explanations

    terms related to celebrities and their professions

    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
    mites
    -0.08
    ohana
    -0.07
    kees
    -0.07
    ¶Į
    -0.07
    ÑĥÑĩа
    -0.07
     Erd
    -0.07
    ismet
    -0.07
    visa
    -0.07
    imat
    -0.07
    ibles
    -0.07
    POSITIVE LOGITS
     cum
    0.07
     who
    0.07
     whom
    0.06
     Cotton
    0.06
    åħ¼
    0.06
     having
    0.06
    kov
    0.06
    0.06
     funnel
    0.05
     slowly
    0.05
    Activations Density 0.007%

    No Known Activations