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. 10-LLAMASCOPE-RES-32K
    6. 11242
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eview
    -0.17
    calar
    -0.16
    acom
    -0.15
     åĥ
    -0.15
    boats
    -0.15
     ков
    -0.15
    essel
    -0.14
    linger
    -0.14
    assist
    -0.14
     gamle
    -0.14
    POSITIVE LOGITS
    ãĥ©ãĤ¹
    0.15
     bunch
    0.14
    ìĹ´
    0.14
    691
    0.14
    /port
    0.13
     circ
    0.13
     Bou
    0.13
    mouseup
    0.13
     bump
    0.13
     Twe
    0.13
    Activations Density 0.001%

    No Known Activations