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. 21274
    Prev
    Next
    INDEX
    Explanations

    references to technology products and services

    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
    zen
    -0.17
    azen
    -0.16
    xm
    -0.15
    ainer
    -0.15
    IXEL
    -0.14
    steen
    -0.14
    obel
    -0.14
    avr
    -0.13
    PostBack
    -0.13
     pul
    -0.13
    POSITIVE LOGITS
    uesta
    0.15
    çħ§
    0.15
     Nu
    0.14
    anka
    0.13
    zzo
    0.13
    ucha
    0.13
    itan
    0.13
     Lebens
    0.13
    ouri
    0.13
    ucc
    0.13
    Activations Density 0.046%

    No Known Activations