© 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. 17-LLAMASCOPE-RES-32K
    11. 18557
    Prev
    Next
    INDEX
    Explanations

    instances of the word "commit" and its variations, indicating actions related to serious offenses or transgressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammers
    -0.14
    etti
    -0.14
    hints
    -0.14
    èĹ
    -0.14
    arry
    -0.14
    conds
    -0.14
    536
    -0.14
    orro
    -0.13
     TMPro
    -0.13
    ayload
    -0.13
    POSITIVE LOGITS
     acts
    0.19
    tee
    0.18
    ocide
    0.17
    aksi
    0.17
     feats
    0.16
    .NULL
    0.16
    tees
    0.16
     tasks
    0.15
    acts
    0.15
     Hav
    0.15
    Activations Density 0.010%

    No Known Activations