© 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. 17-LLAMASCOPE-RES-32K
    11. 27259
    Prev
    Next
    INDEX
    Explanations

    references to reservations and assigned spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uo
    -0.16
    rat
    -0.15
    leanup
    -0.14
    eniz
    -0.14
    AtPath
    -0.14
    znik
    -0.14
    axon
    -0.14
     بÙĪابة
    -0.14
    veau
    -0.14
     Dalton
    -0.14
    POSITIVE LOGITS
     reserve
    0.52
     reserved
    0.48
     reserves
    0.43
     Reserve
    0.41
     Reserved
    0.40
    reserve
    0.39
    reserved
    0.36
     reservation
    0.35
    Reserved
    0.34
     reserva
    0.33
    Activations Density 0.133%

    No Known Activations