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

    Neuronpedia

    APICircuit 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-32K
    6. 16013
    Prev
    Next
    INDEX
    Explanations

    references to music charts and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prec
    -0.15
    abit
    -0.14
     Gram
    -0.14
    èĻİ
    -0.14
    stras
    -0.14
    umin
    -0.14
    innen
    -0.14
    vise
    -0.14
    ooter
    -0.14
    eren
    -0.14
    POSITIVE LOGITS
    bai
    0.16
    ranÃŃ
    0.15
    iw
    0.14
    ceptor
    0.14
    -Ray
    0.14
    Su
    0.14
    gov
    0.14
    ansa
    0.14
    spot
    0.13
     Tanz
    0.13
    Activations Density 0.009%

    No Known Activations