© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 24149
    Prev
    Next
    INDEX
    Explanations

    phrases and terms emphasizing the importance of highlighting or showcasing specific elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ehler
    -0.18
    nd
    -0.17
    Ñģли
    -0.16
    ivant
    -0.15
    aze
    -0.15
    aggi
    -0.15
    åĿĬ
    -0.15
    ìĬ¬
    -0.14
    ationally
    -0.14
    noÅĽci
    -0.14
    POSITIVE LOGITS
    ãĥ¥
    0.17
    گر
    0.15
    lett
    0.15
    relude
    0.15
    ened
    0.15
    listing
    0.14
    799
    0.14
    tement
    0.14
     reel
    0.14
    eous
    0.14
    Activations Density 0.033%

    No Known Activations