Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 10766
    Prev
    Next
    INDEX
    Explanations

    references to budgeting and spending in educational contexts

    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
    VRT
    -0.16
    ximo
    -0.15
    емон
    -0.14
    jsp
    -0.13
    eum
    -0.13
    erable
    -0.13
    odom
    -0.13
    uiltin
    -0.12
    indow
    -0.12
    emer
    -0.12
    POSITIVE LOGITS
     per
    1.22
    _per
    0.76
    per
    0.76
     Per
    0.71
    -per
    0.67
    Per
    0.66
    .per
    0.62
    (per
    0.56
    _PER
    0.56
     PER
    0.54
    Activations Density 0.198%

    No Known Activations