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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 30-LLAMASCOPE-RES-32K
    6. 4573
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orio
    -0.18
    rong
    -0.17
    mx
    -0.16
    HDR
    -0.15
     uv
    -0.15
    inq
    -0.15
     å¾
    -0.15
    δη
    -0.15
    CustomAttributes
    -0.14
    æĽ°
    -0.14
    POSITIVE LOGITS
    caf
    0.17
     Roman
    0.16
    ib
    0.15
    STM
    0.15
     designs
    0.14
    continued
    0.14
     ÐłÐ¾Ð¼
    0.13
    ìĩ
    0.13
    é¡Ķ
    0.13
    uze
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.