© 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. 30-LLAMASCOPE-RES-32K
    11. 24082
    Prev
    Next
    INDEX
    Explanations

    discussions on academic publication and scholarly activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pumping
    -0.19
     pumps
    -0.18
    406
    -0.16
    pip
    -0.16
    perc
    -0.16
     pivot
    -0.16
    pivot
    -0.16
     pump
    -0.15
     peg
    -0.15
     pigeon
    -0.15
    POSITIVE LOGITS
     Paul
    1.30
    Paul
    1.14
     paul
    1.05
     PA
    0.66
     Paulo
    0.59
    PA
    0.57
     Paula
    0.56
    aul
    0.51
     ÐŁÐ¾Ð»
    0.50
    _PA
    0.46
    Activations Density 0.025%

    No Known Activations