© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 11108
    Prev
    Next
    INDEX
    Explanations

    recommendations for engaging content or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urvey
    -0.14
    μÏĢο
    -0.14
     ارائÙĩ
    -0.14
    Æł
    -0.14
     only
    -0.14
     cram
    -0.13
     apenas
    -0.13
    ebi
    -0.13
    enton
    -0.13
     ebp
    -0.13
    POSITIVE LOGITS
     check
    0.32
    check
    0.29
    Check
    0.28
     checks
    0.28
     checking
    0.27
     Check
    0.27
    .check
    0.26
     CHECK
    0.25
     definitely
    0.25
     checked
    0.25
    Activations Density 0.140%

    No Known Activations