© 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. 27-LLAMASCOPE-RES-32K
    11. 15688
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'U' and its variations, likely indicating references to brands or products associated with that letter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avy
    -0.17
    antis
    -0.15
    nst
    -0.14
    輪
    -0.14
    รม
    -0.14
    alsy
    -0.14
    indr
    -0.14
    pecially
    -0.14
    nim
    -0.13
    noop
    -0.13
    POSITIVE LOGITS
    asin
    0.21
    trecht
    0.21
    pto
    0.18
    pton
    0.18
    prising
    0.18
    ppers
    0.17
    å®Ļ
    0.16
    eda
    0.15
    477
    0.15
    ovo
    0.15
    Activations Density 0.037%

    No Known Activations