© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 31290
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and phrases indicating self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Messaging
    -0.20
     Mold
    -0.17
     molding
    -0.17
     Morrison
    -0.17
     Mastery
    -0.16
     Murdoch
    -0.16
     Milo
    -0.16
     Morse
    -0.16
     Mobility
    -0.15
    Mari
    -0.15
    POSITIVE LOGITS
     mean
    0.83
    mean
    0.69
     Mean
    0.66
     means
    0.62
    Mean
    0.59
     ME
    0.57
    _mean
    0.57
    -mean
    0.55
    .mean
    0.54
     meant
    0.53
    Activations Density 0.170%

    No Known Activations