© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 83
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases related to sporting events and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iminal
    -0.17
    fdc
    -0.17
    _tC
    -0.15
    ikat
    -0.15
     danmark
    -0.15
    Ä±ÅŁÄ±k
    -0.14
    emma
    -0.14
    _DLL
    -0.14
    899
    -0.14
    636
    -0.14
    POSITIVE LOGITS
     bi
    0.20
     Bi
    0.17
     super
    0.16
     Pale
    0.16
    ales
    0.16
    //{{
    0.16
     Super
    0.16
    Bi
    0.16
     san
    0.15
     Ryder
    0.15
    Activations Density 0.026%

    No Known Activations