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. 14-LLAMASCOPE-RES-32K
    6. 12546
    Prev
    Next
    INDEX
    Explanations

    URLs and web-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enty
    -0.18
    ensis
    -0.15
    æİĴ
    -0.15
    вен
    -0.14
    auss
    -0.14
    allis
    -0.14
    licit
    -0.14
    ollah
    -0.14
    CUS
    -0.14
     Pic
    -0.14
    POSITIVE LOGITS
     Milo
    0.16
    .DataTable
    0.14
    άλ
    0.14
     ì°©
    0.14
    ond
    0.14
    nám
    0.14
     ÙĪÛĮÚ©ÛĮ
    0.14
    cache
    0.14
    decorate
    0.14
    fox
    0.13
    Activations Density 0.012%

    No Known Activations