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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-LLAMASCOPE-RES-32K
    6. 29547
    Prev
    Next
    INDEX
    Explanations

    terms related to quantifiable metrics in business and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zb
    -0.16
    lassen
    -0.16
    bid
    -0.15
    ook
    -0.14
     Price
    -0.14
    032
    -0.14
    (.)
    -0.14
     classic
    -0.14
    zo
    -0.14
    long
    -0.14
    POSITIVE LOGITS
    âĸį
    0.14
    ieux
    0.14
    addir
    0.13
    oteric
    0.13
    etxt
    0.13
    ursive
    0.13
    inflate
    0.13
    à¸Ńà¸Ń
    0.13
    æĿ¡
    0.13
    AMESPACE
    0.13
    Activations Density 0.638%

    No Known Activations