© 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. 15332
    Prev
    Next
    INDEX
    Explanations

    code-related syntaxes and constructs

    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
     Zem
    -0.14
    unks
    -0.13
    rien
    -0.13
    Äįas
    -0.13
    deaux
    -0.13
     Fuk
    -0.13
    ested
    -0.13
     Caucasian
    -0.12
    Ø·ÙĦ
    -0.12
    igon
    -0.12
    POSITIVE LOGITS
     [=
    0.17
    (IService
    0.16
     your
    0.15
    ÅĤad
    0.15
     [âĢ¦
    0.14
    UIS
    0.14
    usch
    0.14
    .some
    0.13
    .tie
    0.13
    eus
    0.13
    Activations Density 0.076%

    No Known Activations