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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104107
    Prev
    Next
    INDEX
    Explanations

    references to "stone" in various contexts

    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
    OwnProperty
    -0.09
    rael
    -0.08
    teen
    -0.08
    ustin
    -0.08
    ohn
    -0.08
    ìĦł
    -0.08
    uta
    -0.07
    wd
    -0.07
    rias
    -0.07
    pers
    -0.07
    POSITIVE LOGITS
    cipher
    0.11
    pile
    0.08
    house
    0.08
    andalone
    0.08
    craft
    0.08
    ardy
    0.07
    iffer
    0.07
    ÄĽÅĻ
    0.07
    oppable
    0.07
    eliness
    0.07
    Activations Density 0.011%

    No Known Activations