Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 8002
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related concepts in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esel
    -0.15
    lich
    -0.15
     Seeds
    -0.15
     <!--[
    -0.14
    Ñĸв
    -0.14
    аÑĢов
    -0.14
    chen
    -0.13
    707
    -0.13
     view
    -0.13
    fect
    -0.13
    POSITIVE LOGITS
     models
    0.33
    models
    0.27
    .models
    0.26
    (models
    0.26
    =models
    0.25
     Models
    0.24
    /models
    0.22
    _models
    0.22
    IntegerField
    0.20
     fields
    0.20
    Activations Density 0.011%

    No Known Activations