© 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. 20-LLAMASCOPE-RES-32K
    11. 8925
    Prev
    Next
    INDEX
    Explanations

    instances of confusion or mix-ups in identity or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (QL
    -0.15
    rimon
    -0.14
    ansen
    -0.14
    reau
    -0.14
    uzzi
    -0.14
    inton
    -0.14
    idi
    -0.14
    eydi
    -0.14
    itom
    -0.14
    luet
    -0.14
    POSITIVE LOGITS
     confusion
    0.77
     confused
    0.67
     confuse
    0.65
     confusing
    0.56
     mistaken
    0.46
     mistake
    0.45
     mist
    0.44
     Conf
    0.42
     Mist
    0.42
     conf
    0.40
    Activations Density 0.332%

    No Known Activations