© 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. 24-LLAMASCOPE-RES-32K
    11. 11951
    Prev
    Next
    INDEX
    Explanations

    punctuated questions and expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IsNot
    -0.16
    ysi
    -0.15
    acades
    -0.13
    ÏĥÏĦε
    -0.13
    olynomial
    -0.13
    ÙİÙĬ
    -0.13
    ropic
    -0.13
    ÑĥÑĤ
    -0.12
     Cheers
    -0.12
    innen
    -0.12
    POSITIVE LOGITS
     well
    1.11
     Well
    0.98
    well
    0.96
    Well
    0.91
     WELL
    0.88
     bien
    0.69
    "Well
    0.60
     wells
    0.59
    “Well
    0.59
     wellbeing
    0.53
    Activations Density 0.198%

    No Known Activations