© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 8138
    Prev
    Next
    INDEX
    Explanations

    positive aspects and opportunities related to language exchange and tutoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    textAlign
    -0.15
    /token
    -0.15
    tur
    -0.13
    timeline
    -0.13
    /table
    -0.13
    itest
    -0.13
    tak
    -0.13
    /Table
    -0.12
    tile
    -0.12
    InitStruct
    -0.12
    POSITIVE LOGITS
     T
    1.43
    T
    0.95
    ÂłT
    0.85
    :T
    0.75
    .T
    0.73
    {T
    0.72
    =T
    0.70
     Т
    0.70
     ت
    0.69
    *T
    0.68
    Activations Density 0.958%

    No Known Activations