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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 1719
    Prev
    Next
    INDEX
    Explanations

    descriptions of condition or quality, particularly relating to excellence or good shape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kabil
    -0.14
    _barrier
    -0.14
    UMB
    -0.14
    _backend
    -0.14
    Formatting
    -0.13
    umb
    -0.13
    à¹Ģà¸ļ
    -0.13
    enus
    -0.13
     umb
    -0.13
    iling
    -0.13
    POSITIVE LOGITS
     shape
    0.56
     condition
    0.50
     Shape
    0.42
    shape
    0.41
     Condition
    0.40
    condition
    0.37
    Condition
    0.34
     shapes
    0.33
    Shape
    0.33
     CONDITION
    0.32
    Activations Density 0.049%

    No Known Activations