© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 30407
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "constant" in various contexts within mathematical or programming-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hook
    -0.17
    rist
    -0.16
    erson
    -0.16
    ust
    -0.15
    lez
    -0.14
    los
    -0.14
    raft
    -0.14
    _nama
    -0.14
    ullet
    -0.14
    заб
    -0.14
    POSITIVE LOGITS
    ignum
    0.17
    rophic
    0.17
    antly
    0.14
     beden
    0.13
    .Formatter
    0.13
    Scaler
    0.13
     Constant
    0.13
    .DataTable
    0.13
    нен
    0.13
    oir
    0.13
    Activations Density 0.028%

    No Known Activations