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. 15852
    Prev
    Next
    INDEX
    Explanations

    contextual references to formal or structured guidelines or documents

    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
    ROME
    -0.14
    asia
    -0.14
    lod
    -0.14
    abei
    -0.14
    Func
    -0.14
    atics
    -0.13
     Amar
    -0.13
    plementation
    -0.13
    bl
    -0.13
    FUNC
    -0.13
    POSITIVE LOGITS
    GLE
    0.16
    ãĥ¼ãĥª
    0.14
    .po
    0.14
    (fullfile
    0.14
    eneg
    0.14
    _allow
    0.14
    inois
    0.14
    oleon
    0.14
    acre
    0.13
    æ¬ł
    0.13
    Activations Density 0.016%

    No Known Activations