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. 27-LLAMASCOPE-RES-32K
    6. 10681
    Prev
    Next
    INDEX
    Explanations

    weight and capacity specifications related to products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è͵
    -0.17
    chwitz
    -0.16
    utom
    -0.16
    ruk
    -0.16
    aley
    -0.16
    863
    -0.14
    udoku
    -0.14
    ourt
    -0.14
    itz
    -0.14
    xn
    -0.14
    POSITIVE LOGITS
     pound
    0.66
     pounds
    0.63
     lb
    0.54
     Pound
    0.53
     lbs
    0.53
    -pound
    0.53
    lb
    0.48
    lbs
    0.48
     LB
    0.42
     kil
    0.42
    Activations Density 0.075%

    No Known Activations