© 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. 26-LLAMASCOPE-RES-32K
    11. 13737
    Prev
    Next
    INDEX
    Explanations

    terms related to health and wellness topics, specifically focusing on weight loss and dieting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adian
    -0.14
     ¶
    -0.14
    s
    -0.14
     pylint
    -0.14
     http
    -0.13
     //
    -0.13
     ÂŃ
    -0.13
    eken
    -0.13
    uer
    -0.13
     vá»
    -0.13
    POSITIVE LOGITS
    ÑĢаÐ
    0.31
    еÐ
    0.29
    аÐ
    0.25
    оÐ
    0.24
    uC
    0.15
    :class
    0.14
    aN
    0.14
    elib
    0.14
    None
    0.14
    uD
    0.14
    Activations Density 0.564%

    No Known Activations