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. 29-LLAMASCOPE-RES-32K
    6. 3176
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing and document creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onis
    -0.18
    llen
    -0.18
    isphere
    -0.15
    isÃŃ
    -0.15
    ocos
    -0.14
    etus
    -0.14
    erule
    -0.14
    shit
    -0.13
    phant
    -0.13
    REAM
    -0.13
    POSITIVE LOGITS
     restart
    0.20
     Inch
    0.17
    ieu
    0.16
     bure
    0.15
     reun
    0.15
     alist
    0.15
    ymax
    0.15
     clinic
    0.15
     Erg
    0.15
     erg
    0.15
    Activations Density 0.011%

    No Known Activations