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. 29-LLAMASCOPE-RES-32K
    6. 12429
    Prev
    Next
    INDEX
    Explanations

    negative punctuation or symbols indicating strong disapproval

    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
    ungan
    -0.16
    rish
    -0.15
     Mali
    -0.15
    .Metro
    -0.14
    XObject
    -0.14
     crossorigin
    -0.14
    noc
    -0.14
    .jet
    -0.14
    ;br
    -0.14
    ousel
    -0.13
    POSITIVE LOGITS
     Watches
    0.27
     watches
    0.26
     watch
    0.23
    -watch
    0.22
     Hy
    0.21
     wearer
    0.21
    watch
    0.20
    _watch
    0.20
     Basel
    0.20
    Hy
    0.20
    Activations Density 0.000%

    No Known Activations