Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5753
    Prev
    Next
    INDEX
    Explanations

    names of organizations and institutions related to urban land use and planning

    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
    INGLE
    -0.06
    clave
    -0.06
    Sizer
    -0.05
     ÙĪÙĦÙĬ
    -0.05
    userData
    -0.05
    utters
    -0.05
    iš
    -0.05
    Compound
    -0.05
    axter
    -0.05
    ìķ¼
    -0.05
    POSITIVE LOGITS
    (Un
    0.09
    /U
    0.08
     اش
    0.07
    iless
    0.07
    /umd
    0.07
    (UI
    0.07
    (æ°´
    0.07
    (U
    0.07
    SingleOrDefault
    0.07
     FetchType
    0.06
    Activations Density 0.076%

    No Known Activations