© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19-LLAMASCOPE-RES-32K
    11. 27378
    Prev
    Next
    INDEX
    Explanations

    references to original works and their adaptations or variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rum
    -0.16
    orts
    -0.15
    rve
    -0.14
    lien
    -0.14
     upcoming
    -0.14
     forthcoming
    -0.14
    онÑĥ
    -0.14
     sắp
    -0.13
    veÅĻej
    -0.13
    trand
    -0.13
    POSITIVE LOGITS
     original
    1.18
    original
    1.00
     originally
    0.96
     originals
    0.93
     Original
    0.91
     ORIGINAL
    0.86
    Original
    0.85
    -original
    0.84
    (original
    0.79
    _original
    0.79
    Activations Density 0.419%

    No Known Activations