© 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. 26766
    Prev
    Next
    INDEX
    Explanations

    phrases that express a sense of observation or witnessing ongoing changes or events

    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
    ongyang
    -0.17
    tring
    -0.16
    /fw
    -0.16
    bpp
    -0.16
    olib
    -0.16
    uled
    -0.16
    raith
    -0.16
    AGMA
    -0.15
    ius
    -0.15
    zdy
    -0.15
    POSITIVE LOGITS
    è
    0.17
     Eld
    0.14
     IReadOnly
    0.14
     tender
    0.13
    esse
    0.13
     conf
    0.13
     unfold
    0.13
    aney
    0.13
    ushman
    0.13
    202
    0.13
    Activations Density 0.165%

    No Known Activations