© 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. 71119
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jacqueline."

    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
    θο
    -0.08
    staking
    -0.07
     personals
    -0.06
    매
    -0.06
    fuse
    -0.06
    unge
    -0.06
    ุà¸Ĥ
    -0.06
    ált
    -0.06
    cobra
    -0.06
    afone
    -0.06
    POSITIVE LOGITS
    erif
    0.07
    ettel
    0.07
    cer
    0.07
    enheim
    0.07
    ques
    0.07
    пп
    0.07
    uzzi
    0.06
    891
    0.06
    .running
    0.06
     Running
    0.06
    Activations Density 0.006%

    No Known Activations