© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 19061
    Prev
    Next
    INDEX
    Explanations

    references to job cuts and budget reductions

    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
    adil
    -0.14
    ftar
    -0.14
    æĭľ
    -0.14
    Deposit
    -0.13
    ewing
    -0.13
    $insert
    -0.13
     ontvangst
    -0.13
    UFFIX
    -0.13
    ctal
    -0.13
    ango
    -0.12
    POSITIVE LOGITS
     cuts
    0.50
     cut
    0.43
    cuts
    0.38
     CUT
    0.37
     Cut
    0.35
    cut
    0.32
    -cut
    0.32
    Cut
    0.31
    .cut
    0.30
    _cut
    0.30
    Activations Density 0.119%

    No Known Activations