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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 6948
    Prev
    Next
    INDEX
    Explanations

    information related to ski resorts and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sefer
    -0.15
     zar
    -0.14
    shore
    -0.14
    /tos
    -0.14
    odu
    -0.14
     stall
    -0.14
    inger
    -0.14
     Flores
    -0.13
    etsy
    -0.13
     submarine
    -0.13
    POSITIVE LOGITS
     ski
    0.52
     Ski
    0.47
     skiing
    0.45
    SKI
    0.40
     snow
    0.39
    ski
    0.37
    snow
    0.34
     resort
    0.33
    Snow
    0.33
     resorts
    0.33
    Activations Density 0.128%

    No Known Activations