© 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. 21889
    Prev
    Next
    INDEX
    Explanations

    conditions or hypothetical scenarios involving the word "if."

    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
    otor
    -0.16
    cle
    -0.15
    ython
    -0.15
    inski
    -0.15
    .annot
    -0.15
    anka
    -0.14
     Cle
    -0.14
    axon
    -0.14
    elin
    -0.14
    elson
    -0.14
    POSITIVE LOGITS
     Lansing
    0.16
    bx
    0.15
    ouri
    0.15
    liš
    0.15
     mimetype
    0.15
    òi
    0.14
    è¶Ĭ
    0.14
    .Transparent
    0.14
    .CreateDirectory
    0.14
     matte
    0.14
    Activations Density 0.007%

    No Known Activations