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. 6-LLAMASCOPE-RES-32K
    6. 21526
    Prev
    Next
    INDEX
    Explanations

    collective pronouns and references to teamwork or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿŁ
    -0.15
    NEY
    -0.15
    ubb
    -0.14
    retweeted
    -0.14
    CCI
    -0.14
    .alert
    -0.14
    ropa
    -0.14
    rupa
    -0.14
    hetto
    -0.14
    emat
    -0.14
    POSITIVE LOGITS
    ses
    0.17
    ylon
    0.15
    797
    0.14
    wheel
    0.14
    plete
    0.14
    ibo
    0.14
    /Home
    0.14
    ẽ
    0.14
    orget
    0.14
     Blender
    0.14
    Activations Density 0.024%

    No Known Activations