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. 25-LLAMASCOPE-RES-32K
    6. 22680
    Prev
    Next
    INDEX
    Explanations

    the name of a specific individual or entity, particularly in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inh
    -0.14
    ãĥ¼ãĥĭ
    -0.14
    linger
    -0.14
    .ordinal
    -0.14
     âĢ»
    -0.14
     aras
    -0.13
     Polo
    -0.13
     tas
    -0.13
    Å¡tÄĽnÃŃ
    -0.13
    zell
    -0.13
    POSITIVE LOGITS
     ÑĤеж
    0.16
     pund
    0.16
    grass
    0.15
     ragaz
    0.15
    Qty
    0.15
     qty
    0.15
     Ist
    0.14
    kov
    0.14
    ocaly
    0.14
    ffff
    0.14
    Activations Density 0.000%

    No Known Activations