© 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. 18-LLAMASCOPE-RES-32K
    11. 8891
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "on" and related phrases in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Humb
    -0.17
     Geile
    -0.16
     Redistributions
    -0.15
    lf
    -0.15
    amarin
    -0.14
    @email
    -0.13
     anomal
    -0.13
    butt
    -0.13
    htag
    -0.13
    ÑĥÑĢн
    -0.13
    POSITIVE LOGITS
    isci
    0.17
    etin
    0.15
    oftware
    0.15
    appen
    0.14
    º
    0.14
    Untitled
    0.14
    eneg
    0.13
    Guest
    0.13
    _printer
    0.13
     spect
    0.13
    Activations Density 0.024%

    No Known Activations