© 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 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. 12-LLAMASCOPE-RES-32K
    11. 24770
    Prev
    Next
    INDEX
    Explanations

    specific brands or known entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kemp
    -0.16
     Ekon
    -0.14
    pedia
    -0.14
     Sentence
    -0.14
     Favor
    -0.13
    ObjectContext
    -0.13
    osoph
    -0.13
     Bri
    -0.13
    екаÑĢ
    -0.13
    Ģë¡ľ
    -0.13
    POSITIVE LOGITS
    eza
    0.14
    æ½
    0.14
     Howell
    0.14
    é¼
    0.14
    ãĥ¼ãĥĩ
    0.14
     paras
    0.13
    adius
    0.13
    tains
    0.13
    .await
    0.13
    rane
    0.12
    Activations Density 0.015%

    No Known Activations