© 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. 6-LLAMASCOPE-RES-32K
    11. 19706
    Prev
    Next
    INDEX
    Explanations

    connections that emphasize assertions or statements of assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osh
    -0.18
    okus
    -0.16
    ocker
    -0.15
    ì²´
    -0.15
     Möglich
    -0.15
    кÑĥл
    -0.14
    eth
    -0.14
     Pur
    -0.13
    iera
    -0.13
    efeller
    -0.13
    POSITIVE LOGITS
    ceae
    0.15
    alink
    0.15
    cio
    0.15
    ingham
    0.14
    .plist
    0.14
    اتÙĩ
    0.14
    ваÑĢ
    0.14
    enie
    0.13
    piring
    0.13
     京
    0.13
    Activations Density 0.029%

    No Known Activations