© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 25-LLAMASCOPE-RES-32K
    11. 19755
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Suzanne" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÏĨÏĮ
    -0.16
    lops
    -0.16
    zl
    -0.16
    ropol
    -0.14
    stras
    -0.14
     prospect
    -0.14
    оÑī
    -0.14
    кÑĥÑģ
    -0.14
    axies
    -0.14
    krom
    -0.14
    POSITIVE LOGITS
    hou
    0.28
    ze
    0.21
    eration
    0.17
    uka
    0.17
    amm
    0.17
    ifix
    0.16
    hong
    0.16
    ambique
    0.15
    ¢ħ
    0.15
    za
    0.15
    Activations Density 0.017%

    No Known Activations