© 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. 17-LLAMASCOPE-RES-32K
    6. 20280
    Prev
    Next
    INDEX
    Explanations

    descriptors of user interface quality and ease of use

    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
     Bench
    -0.15
    beck
    -0.15
    criptor
    -0.15
     getArguments
    -0.14
    pector
    -0.14
    kü
    -0.14
    ÑģÑĤав
    -0.13
    inky
    -0.13
    .Networking
    -0.13
    gens
    -0.13
    POSITIVE LOGITS
     interface
    0.25
     Interface
    0.23
    Interface
    0.22
    _interface
    0.21
    interface
    0.21
     user
    0.20
     navigation
    0.20
     navig
    0.20
     Navigation
    0.20
    experience
    0.19
    Activations Density 0.227%

    No Known Activations