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. 17-LLAMASCOPE-RES-32K
    6. 25840
    Prev
    Next
    INDEX
    Explanations

    financial metrics and timelines associated with business or technology events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    202
    -0.32
     covid
    -0.29
     COVID
    -0.29
     bush
    -0.27
     Tik
    -0.26
     Covid
    -0.26
     Axios
    -0.25
    200
    -0.25
    ðĿ
    -0.24
     ðĿ
    -0.24
    POSITIVE LOGITS
    201
    0.35
     xrange
    0.32
     âĢª
    0.31
     Ebola
    0.29
     Hollande
    0.29
     Occupy
    0.28
     Kinect
    0.27
     tumblr
    0.26
     glyphicon
    0.26
     Obamacare
    0.26
    Activations Density 0.868%

    No Known Activations