© 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. 18-LLAMASCOPE-RES-32K
    11. 10102
    Prev
    Next
    INDEX
    Explanations

    significant scenes and moments from television or film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eshire
    -0.16
    orts
    -0.15
    äºŃ
    -0.15
    éĢĤ
    -0.15
    ernote
    -0.14
     groove
    -0.14
    éģ©
    -0.14
     اÙĦØ£ÙĨ
    -0.14
    @testable
    -0.14
    chein
    -0.14
    POSITIVE LOGITS
     scene
    0.35
     scenes
    0.34
     Scene
    0.32
    Scene
    0.27
     Scenes
    0.27
    scene
    0.25
     sequences
    0.25
    scenes
    0.24
    -scenes
    0.23
    _scene
    0.23
    Activations Density 0.201%

    No Known Activations