© 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. 28-LLAMASCOPE-RES-32K
    11. 22665
    Prev
    Next
    INDEX
    Explanations

    references to databases and professional judgment in various contexts

    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
    egrator
    -0.12
    çĶ³åįļ
    -0.12
    GuidId
    -0.12
    ÑĨез
    -0.11
    SCII
    -0.11
    \htdocs
    -0.11
    adla
    -0.11
    PÅĻÃŃ
    -0.11
    groupon
    -0.10
    KHTML
    -0.10
    POSITIVE LOGITS
     J
    0.83
    J
    0.79
    -j
    0.75
    _j
    0.73
    -J
    0.69
    _J
    0.68
     j
    0.68
    .J
    0.64
    .j
    0.62
    j
    0.60
    Activations Density 1.496%

    No Known Activations