© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 17495
    Prev
    Next
    INDEX
    Explanations

    content related to access and availability of various resources, especially in academic and media contexts

    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
    ¼åIJĪ
    -0.15
    yer
    -0.13
    ardım
    -0.13
    eyse
    -0.13
    ì£
    -0.12
    strup
    -0.12
    λαν
    -0.12
    aises
    -0.12
    à¥įवर
    -0.12
    ersh
    -0.12
    POSITIVE LOGITS
     available
    0.78
     avail
    0.68
    available
    0.67
     ava
    0.63
     aval
    0.63
    -available
    0.59
     readily
    0.58
     Available
    0.56
     AVAILABLE
    0.55
     accessible
    0.54
    Activations Density 0.276%

    No Known Activations