© 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. 16-LLAMASCOPE-RES-32K
    11. 18473
    Prev
    Next
    INDEX
    Explanations

    elements and events related to user interactions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abi
    -0.15
    óż
    -0.15
    .createComponent
    -0.15
     plugs
    -0.14
    ehr
    -0.14
     ØŃØ°
    -0.14
    illez
    -0.14
    LN
    -0.14
    ëĮĢ
    -0.13
     BaseEntity
    -0.13
    POSITIVE LOGITS
     upon
    0.21
     Shea
    0.16
     enemy
    0.16
     after
    0.15
     when
    0.15
    azen
    0.15
     cycle
    0.15
     initial
    0.15
    Finite
    0.15
     Enemy
    0.15
    Activations Density 0.097%

    No Known Activations