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. 25-LLAMASCOPE-RES-32K
    6. 22585
    Prev
    Next
    INDEX
    Explanations

    programming commands and SQL query structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .updateDynamic
    -0.15
    CJK
    -0.14
    _strerror
    -0.14
    PWD
    -0.14
    /epl
    -0.13
    hotmail
    -0.13
    alue
    -0.13
    kud
    -0.13
    /******/
    -0.13
    haven
    -0.13
    POSITIVE LOGITS
    aram
    0.17
    611
    0.15
    onest
    0.13
    кова
    0.13
    uet
    0.13
    894
    0.13
    ово
    0.13
    050
    0.13
    unn
    0.13
    036
    0.13
    Activations Density 0.408%

    No Known Activations