© 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. 31-LLAMASCOPE-RES-32K
    11. 21804
    Prev
    Next
    INDEX
    Explanations

    references to outstanding customer service experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?”↵↵
    -0.13
    ?"↵↵
    -0.12
    .LayoutStyle
    -0.12
    ").↵↵
    -0.11
    ?)↵↵
    -0.11
     spÃŃÅ¡e
    -0.11
    )?↵↵
    -0.11
    ),↵↵
    -0.11
    "),↵↵
    -0.10
    ":↵↵
    -0.10
    POSITIVE LOGITS
    !↵
    0.71
    !
    0.68
    !!↵
    0.66
    !!
    0.63
    !!!↵
    0.63
    !!!
    0.60
     !↵
    0.59
    !!!!
    0.57
    !.
    0.55
     !
    0.53
    Activations Density 14.214%

    No Known Activations