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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95800
    Prev
    Next
    INDEX
    Explanations

    concepts related to strengths and weaknesses

    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
    oce
    -0.08
    cio
    -0.07
    otton
    -0.07
    CLUDING
    -0.07
    ocy
    -0.07
    oze
    -0.07
    iggers
    -0.07
    usted
    -0.07
    erce
    -0.06
    eton
    -0.06
    POSITIVE LOGITS
    ÚĨار
    0.06
    folios
    0.06
    ably
    0.06
    ful
    0.06
    erner
    0.06
    741
    0.06
    rich
    0.06
    utzer
    0.06
    fully
    0.06
    full
    0.06
    Activations Density 0.009%

    No Known Activations