© 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. 84423
    Prev
    Next
    INDEX
    Explanations

    mentions of "Brooklyn"

    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
    ye
    -0.07
    yun
    -0.07
    y
    -0.07
    ylation
    -0.07
    yr
    -0.07
    ãĥĨãĥ«
    -0.06
    tir
    -0.06
    yonel
    -0.06
    si
    -0.06
    sel
    -0.06
    POSITIVE LOGITS
    ites
    0.10
    ized
    0.07
    ights
    0.07
    ìĹĦ
    0.07
    ite
    0.07
    mania
    0.07
    eways
    0.07
    ekim
    0.07
    coli
    0.07
    -central
    0.07
    Activations Density 0.007%

    No Known Activations