© 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. 16862
    Prev
    Next
    INDEX
    Explanations

    specific patterns and sequences in words, particularly character combinations and string anomalies

    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
    ợ
    -0.15
    .removeListener
    -0.15
    empt
    -0.15
     Bras
    -0.15
    adel
    -0.15
    nee
    -0.14
    iscal
    -0.14
    νομ
    -0.13
    /repos
    -0.13
    IDEO
    -0.13
    POSITIVE LOGITS
    rs
    0.38
    r
    0.35
     r
    0.34
    르
    0.33
    ר
    0.32
    'r
    0.31
    rcode
    0.30
    å°Ķ
    0.30
    ÑĢ
    0.29
    र
    0.28
    Activations Density 0.116%

    No Known Activations