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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55382
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with rhymes and rhythmic patterns

    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
    oren
    -0.07
     ReactDOM
    -0.07
    esini
    -0.07
    ovu
    -0.07
    ITO
    -0.07
    ito
    -0.07
    ات
    -0.06
    tering
    -0.06
    lay
    -0.06
    weg
    -0.06
    POSITIVE LOGITS
     rh
    0.07
    azon
    0.07
    NullOr
    0.07
    аÐ
    0.07
     Rh
    0.07
    Ø®
    0.07
    ingly
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    abilit
    0.06
     Maiden
    0.06
    Activations Density 0.002%

    No Known Activations