© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 5775
    Prev
    Next
    INDEX
    Explanations

    occurrences of words or patterns that contain the letter "m."

    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
    isté
    -0.16
     Mirror
    -0.15
     Macro
    -0.15
    ANDING
    -0.15
    ordo
    -0.15
    ATUS
    -0.15
     yön
    -0.15
    γή
    -0.15
    Macro
    -0.14
    itet
    -0.14
    POSITIVE LOGITS
    ice
    0.23
    angers
    0.23
    ement
    0.23
    usters
    0.22
    enus
    0.21
    ummies
    0.21
    achines
    0.21
    osa
    0.20
    igrations
    0.20
    ammo
    0.20
    Activations Density 0.027%

    No Known Activations