© 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. 16497
    Prev
    Next
    INDEX
    Explanations

    instances of transformation or pivotal moments in narratives or arguments

    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
    /Page
    -0.15
     Preston
    -0.14
    æĸ¯çī¹
    -0.13
    :@"%@
    -0.13
    antz
    -0.13
    andes
    -0.12
    ÙİÙī
    -0.12
    ılı
    -0.12
    pak
    -0.12
    ÑģиÑĤ
    -0.12
    POSITIVE LOGITS
     point
    1.32
     Point
    1.14
    point
    1.10
    -point
    1.09
     points
    1.09
     POINT
    1.05
    Point
    1.02
    _point
    0.99
    çĤ¹
    0.95
     Points
    0.94
    Activations Density 0.474%

    No Known Activations