© 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. 19-LLAMASCOPE-RES-32K
    11. 26859
    Prev
    Next
    INDEX
    Explanations

    descriptions of relationships or situations involving positions, states, or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irk
    -0.15
    onas
    -0.14
    za
    -0.14
    ÑİÑĢ
    -0.13
     Bowman
    -0.13
     Tato
    -0.13
    lint
    -0.13
     intr
    -0.13
     crown
    -0.13
    _REPO
    -0.13
    POSITIVE LOGITS
     position
    0.23
     mode
    0.22
     ÑģоÑģÑĤоÑıнии
    0.18
     Mode
    0.18
     state
    0.18
    etto
    0.18
     positions
    0.17
    Mode
    0.17
    .Mode
    0.17
     mood
    0.17
    Activations Density 0.219%

    No Known Activations