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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5315
    Prev
    Next
    INDEX
    Explanations

    specific names and related entities 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
    ungle
    -0.08
    wiki
    -0.08
    ži
    -0.07
    webdriver
    -0.07
    vá
    -0.07
     wiki
    -0.07
    insic
    -0.06
    overe
    -0.06
     žal
    -0.06
    wik
    -0.06
    POSITIVE LOGITS
     MW
    0.13
     DW
    0.13
    AW
    0.13
     PW
    0.13
     GW
    0.12
     CW
    0.12
    SW
    0.12
     IW
    0.12
     AW
    0.12
     SW
    0.12
    Activations Density 0.168%

    No Known Activations