© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59153
    Prev
    Next
    INDEX
    Explanations

    references to 'hood' or related terms in various contexts, indicating a focus on community or environment

    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
    holding
    -0.07
    monds
    -0.07
    EDIA
    -0.07
    epy
    -0.07
    кин
    -0.07
    ced
    -0.07
    ecedor
    -0.06
    asaki
    -0.06
    ureen
    -0.06
    innen
    -0.06
    POSITIVE LOGITS
    lum
    0.08
    ie
    0.08
    ed
    0.08
    ridge
    0.08
    less
    0.07
    ĶĦ
    0.07
    ilation
    0.07
    zie
    0.07
    iveau
    0.07
    simd
    0.07
    Activations Density 0.003%

    No Known Activations