© 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. 31-LLAMASCOPE-RES-32K
    6. 2912
    Prev
    Next
    INDEX
    Explanations

    information related to account structures and identifiers in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĴ®
    -0.13
    utschein
    -0.12
    SSIP
    -0.11
    ypad
    -0.11
    ĩ¼
    -0.11
    evin
    -0.11
    unma
    -0.11
    asics
    -0.10
    ัà¸ĵà¸ij
    -0.10
    é½
    -0.10
    POSITIVE LOGITS
     Ar
    1.00
     AR
    0.95
    Ar
    0.95
    -ar
    0.91
    _ar
    0.87
     ar
    0.86
    .Ar
    0.86
    /ar
    0.83
     ÐIJÑĢ
    0.82
    .ar
    0.81
    Activations Density 0.829%

    No Known Activations