© 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. 16-LLAMASCOPE-RES-32K
    11. 9967
    Prev
    Next
    INDEX
    Explanations

    words related to enabling actions or functionalities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãĥ¼ãĥĭ
    -0.17
    svp
    -0.15
    irket
    -0.14
    ogra
    -0.14
    ully
    -0.14
    oenix
    -0.14
    $MESS
    -0.14
    ventus
    -0.14
    uber
    -0.14
    ven
    -0.14
    POSITIVE LOGITS
    /disable
    0.29
     us
    0.26
    ance
    0.19
    ances
    0.17
     you
    0.16
    /dis
    0.16
    ingham
    0.16
    iland
    0.16
    tings
    0.15
    oes
    0.15
    Activations Density 0.011%

    No Known Activations