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. 6-LLAMASCOPE-RES-32K
    6. 25222
    Prev
    Next
    INDEX
    Explanations

    numerical references typically associated with scientific articles or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssp
    -0.14
    ael
    -0.14
    IDAD
    -0.14
    -txt
    -0.13
    ServiceProvider
    -0.13
    /plain
    -0.13
    athom
    -0.13
     plain
    -0.13
    .GroupLayout
    -0.13
    plib
    -0.13
    POSITIVE LOGITS
    atz
    0.20
    arpa
    0.17
    usat
    0.15
    amburger
    0.15
    oug
    0.14
    upert
    0.14
     util
    0.14
     invitations
    0.14
    umpy
    0.13
    us
    0.13
    Activations Density 0.016%

    No Known Activations