© 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. 23-LLAMASCOPE-RES-32K
    11. 21962
    Prev
    Next
    INDEX
    Explanations

    expressions related to gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oine
    -0.15
    edio
    -0.15
    igue
    -0.15
    ventus
    -0.15
    ouz
    -0.14
    .rdf
    -0.14
     Bilim
    -0.14
    ione
    -0.14
    odate
    -0.14
    andbox
    -0.14
    POSITIVE LOGITS
    ola
    0.20
     Lagos
    0.19
     Ol
    0.19
    emi
    0.19
     Ade
    0.18
    iola
    0.18
    erin
    0.17
    ipe
    0.17
    ADED
    0.17
    OLA
    0.17
    Activations Density 0.071%

    No Known Activations