© 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. 24-LLAMASCOPE-RES-32K
    11. 8835
    Prev
    Next
    INDEX
    Explanations

    instructions and requirements related to ice skating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TL
    -0.16
    quip
    -0.15
    дан
    -0.15
    obus
    -0.15
    iffin
    -0.14
    ucchini
    -0.14
    prit
    -0.14
     Agency
    -0.14
    vine
    -0.14
     eskort
    -0.14
    POSITIVE LOGITS
     ice
    0.46
     skating
    0.45
     Ice
    0.38
     figure
    0.35
     sk
    0.35
     ICE
    0.34
     skate
    0.33
    Ice
    0.32
    ice
    0.31
    åĨ°
    0.31
    Activations Density 0.076%

    No Known Activations