Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-LLAMASCOPE-RES-32K
    6. 6113
    Prev
    Next
    INDEX
    Explanations

    prominent names and figures in various contexts or pieces of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oire
    -0.16
    زÛĮ
    -0.15
    åħ¼
    -0.15
    iggins
    -0.14
    agnost
    -0.14
    rror
    -0.14
    _RAW
    -0.14
    nonnull
    -0.14
     赤
    -0.14
    inç
    -0.14
    POSITIVE LOGITS
     work
    0.17
     Work
    0.16
    805
    0.15
    dataTable
    0.15
    Work
    0.14
    _work
    0.14
    949
    0.14
    work
    0.14
    907
    0.14
    ettle
    0.13
    Activations Density 0.034%

    No Known Activations