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. 9-LLAMASCOPE-RES-131K
    6. 96062
    Prev
    Next
    INDEX
    Explanations

    segments that contain numerical data

    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
    inas
    -0.07
    nic
    -0.06
    org
    -0.06
    pic
    -0.06
    ickle
    -0.06
    oid
    -0.06
    linger
    -0.06
    kit
    -0.06
    rais
    -0.06
    atan
    -0.06
    POSITIVE LOGITS
     Stretch
    0.07
    GPC
    0.07
    stretch
    0.07
    ĽĪ
    0.07
    GLOSS
    0.07
    ден
    0.07
    Stretch
    0.07
    raud
    0.07
    ifetime
    0.06
    .Networking
    0.06
    Activations Density 0.000%

    No Known Activations