© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 21410
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sourceMappingURL
    -0.17
     noqa
    -0.16
    oral
    -0.15
    anio
    -0.14
    elts
    -0.14
    ZONE
    -0.14
    urgy
    -0.14
     ÐļÑĢи
    -0.14
    ä¾Ľ
    -0.13
    Specifications
    -0.13
    POSITIVE LOGITS
    yar
    0.16
    ĺ
    0.15
     SSE
    0.15
    ieten
    0.15
    bite
    0.14
    icum
    0.14
    ibar
    0.13
    аÑĢод
    0.13
    umed
    0.13
    ICO
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.