© 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. 17-LLAMASCOPE-RES-131K
    6. 57045
    Prev
    Next
    INDEX
    Explanations

    instances of the number 13 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
    hood
    -0.08
       
    -0.08
    lig
    -0.08
    led
    -0.07
    ings
    -0.07
    sell
    -0.07
    471
    -0.07
    avras
    -0.07
    IgnoreCase
    -0.07
    pers
    -0.07
    POSITIVE LOGITS
    rd
    0.11
    cy
    0.08
    ileo
    0.08
    mites
    0.08
    th
    0.08
    ../../../
    0.08
    ewise
    0.07
    iner
    0.07
    -digit
    0.07
    ivec
    0.07
    Activations Density 0.035%

    No Known Activations