© 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. 20-LLAMASCOPE-RES-32K
    11. 25822
    Prev
    Next
    INDEX
    Explanations

    mentions of "Jud" and related variations, indicating a focus on Judeo-Christian themes or figures

    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
    etics
    -0.18
    ]={↵
    -0.17
    ighted
    -0.16
    ey
    -0.15
    eer
    -0.15
    ivas
    -0.14
    tures
    -0.14
    éĢ¸
    -0.14
     whale
    -0.14
    osate
    -0.14
    POSITIVE LOGITS
    ging
    0.31
    gement
    0.25
    gment
    0.24
    iciary
    0.24
    ges
    0.24
    icial
    0.23
    jud
    0.22
    ged
    0.22
    ger
    0.21
    gements
    0.21
    Activations Density 0.014%

    No Known Activations