© 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. 26-LLAMASCOPE-RES-32K
    11. 7457
    Prev
    Next
    INDEX
    Explanations

    punctuation and conversational markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichi
    -0.17
     said
    -0.16
    说
    -0.16
     diyor
    -0.16
     saying
    -0.16
    say
    -0.15
     Saying
    -0.15
     says
    -0.15
     say
    -0.15
     ÅĻÃŃká
    -0.15
    POSITIVE LOGITS
     adding
    0.21
     referring
    0.20
     refer
    0.19
     reference
    0.18
    reff
    0.17
     réfé
    0.17
    tout
    0.17
     meaning
    0.17
     speaking
    0.17
    adding
    0.17
    Activations Density 0.041%

    No Known Activations