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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43694
    Prev
    Next
    INDEX
    Explanations

    terms related to sculpture and sculptural art

    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
    hani
    -0.07
    hana
    -0.06
    klad
    -0.06
    ISION
    -0.06
    nan
    -0.06
    idth
    -0.06
    è¦
    -0.06
    xima
    -0.06
    ifestyles
    -0.06
    eniz
    -0.06
    POSITIVE LOGITS
    ural
    0.20
    ured
    0.15
    ed
    0.15
    ors
    0.14
    ure
    0.14
    urally
    0.14
    ing
    0.13
    URAL
    0.12
    or
    0.12
    ures
    0.11
    Activations Density 0.005%

    No Known Activations