© 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. 23-LLAMASCOPE-RES-32K
    11. 20589
    Prev
    Next
    INDEX
    Explanations

    mentions of community events and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĤÑĢен
    -0.17
    eteria
    -0.15
    istes
    -0.14
    å¶
    -0.14
    OWNER
    -0.14
    гл
    -0.14
     Ñģв
    -0.14
     minib
    -0.14
     Dinner
    -0.14
    brtc
    -0.13
    POSITIVE LOGITS
     vendors
    0.23
     vendor
    0.23
     Vendor
    0.20
     festival
    0.20
     Parking
    0.20
     admission
    0.19
    vendor
    0.19
    FREE
    0.19
    Vendor
    0.19
     FREE
    0.19
    Activations Density 0.139%

    No Known Activations