© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2347
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reflection or the process of thoughts emerging in one's mind

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    .ali
    -0.16
    zar
    -0.15
    arger
    -0.15
    MASK
    -0.14
    ãĥ³ãĥij
    -0.14
    oya
    -0.14
    _WS
    -0.14
    ystack
    -0.14
    hyth
    -0.14
    _DECLS
    -0.14
    POSITIVE LOGITS
     mind
    1.04
     minds
    0.85
    mind
    0.84
     Mind
    0.82
    Mind
    0.76
     Minds
    0.64
     minded
    0.53
     mente
    0.53
     brain
    0.50
    -minded
    0.41
    Activations Density 0.223%

    No Known Activations