© 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. 83206
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "downtown"

    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
    ayo
    -0.07
    odega
    -0.07
    istor
    -0.07
    سÙĪ
    -0.07
    olum
    -0.06
    ÑĢазÑĥ
    -0.06
    ycl
    -0.06
    apy
    -0.06
    rette
    -0.06
    ÑģÑĤвоÑĢ
    -0.06
    POSITIVE LOGITS
    s
    0.09
    /up
    0.09
     area
    0.08
    /off
    0.08
    /down
    0.08
    ference
    0.08
    /back
    0.08
    /front
    0.07
    för
    0.07
    -area
    0.07
    Activations Density 0.005%

    No Known Activations