© 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. 29-LLAMASCOPE-RES-32K
    11. 20700
    Prev
    Next
    INDEX
    Explanations

    references to fastening mechanisms and their function in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wald
    -0.20
    lify
    -0.17
    orial
    -0.17
    liner
    -0.16
    ted
    -0.16
    falls
    -0.16
    lined
    -0.16
    ervals
    -0.15
    rost
    -0.15
    apult
    -0.15
    POSITIVE LOGITS
    swagen
    0.17
    unteer
    0.16
    omon
    0.16
    ìį¨
    0.16
    iferay
    0.16
    te
    0.15
    ary
    0.15
    à¹īà¸ĩ
    0.15
    ãģĤ
    0.15
    ī
    0.14
    Activations Density 0.137%

    No Known Activations