© 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. 26-LLAMASCOPE-RES-32K
    11. 29987
    Prev
    Next
    INDEX
    Explanations

    discussions about action and resistance related to task initiation and motivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itez
    -0.13
    .sam
    -0.13
    огод
    -0.13
    Ñĩи
    -0.12
    _TRY
    -0.12
    aths
    -0.12
    decltype
    -0.12
    ogo
    -0.12
    구
    -0.12
    ãģªãĤī
    -0.12
    POSITIVE LOGITS
     once
    1.31
    once
    1.16
     Once
    1.06
    Once
    1.04
    _once
    0.74
    .once
    0.69
     einmal
    0.66
    _ONCE
    0.60
    .Once
    0.57
    ä¸Ģ次
    0.53
    Activations Density 0.554%

    No Known Activations