© 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. 25-LLAMASCOPE-RES-32K
    11. 17275
    Prev
    Next
    INDEX
    Explanations

    variations of the word "surreal" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viders
    -0.17
    itele
    -0.16
     reuse
    -0.15
    ska
    -0.15
    /REC
    -0.15
    rote
    -0.14
     prox
    -0.14
    som
    -0.14
    osemite
    -0.14
    Türkiye
    -0.14
    POSITIVE LOGITS
    nder
    0.28
     Surre
    0.25
     surre
    0.23
    alist
    0.23
    URRE
    0.20
    urre
    0.19
    NDER
    0.18
    rend
    0.17
    ault
    0.17
     surrender
    0.17
    Activations Density 0.010%

    No Known Activations