© 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. 29-LLAMASCOPE-RES-32K
    11. 18561
    Prev
    Next
    INDEX
    Explanations

    references to various types of video content and promotional offers

    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
    æ´
    -0.17
    #aa
    -0.16
    /screen
    -0.15
    ofilm
    -0.15
    pane
    -0.14
    sheets
    -0.14
    roadcast
    -0.14
    Netflix
    -0.14
    agle
    -0.14
    akedown
    -0.14
    POSITIVE LOGITS
     commercial
    0.39
     spots
    0.36
     prom
    0.32
     spot
    0.31
     Commercial
    0.30
    commercial
    0.30
     comercial
    0.30
    -commercial
    0.30
     PSA
    0.28
    Commercial
    0.28
    Activations Density 0.121%

    No Known Activations