© 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. 5072
    Prev
    Next
    INDEX
    Explanations

    mentions of skills and practical advice related to horseback riding

    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
    PELL
    -0.15
    odem
    -0.14
    Bloc
    -0.14
     craw
    -0.14
     Panda
    -0.14
     antenn
    -0.14
     Furn
    -0.13
    esser
    -0.13
     seafood
    -0.13
     Craw
    -0.13
    POSITIVE LOGITS
     horse
    0.69
     horses
    0.68
     Horse
    0.63
    horse
    0.60
     equ
    0.50
     riders
    0.47
     rider
    0.47
     riding
    0.46
     pony
    0.45
     saddle
    0.44
    Activations Density 0.164%

    No Known Activations