© 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. 31-LLAMASCOPE-RES-32K
    11. 21086
    Prev
    Next
    INDEX
    Explanations

    expressions or terminology related to age or generational differences

    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
     докÑĥм
    -0.51
     ÑģобÑĭ
    -0.44
     инÑĦоÑĢма
    -0.36
     ÑĤабли
    -0.30
     оÑĢганиза
    -0.26
     назна
    -0.25
     иÑģполÑĮзовани
    -0.24
     ÑĤва
    -0.23
     елек
    -0.22
     ÑģоÑħÑĢа
    -0.22
    POSITIVE LOGITS
     оÑĩенÑĮ
    0.30
     доволÑĮно
    0.29
     доÑģÑĤаÑĤоÑĩно
    0.28
     более
    0.25
     ÑħоÑĢоÑĪо
    0.24
     болÑĮÑĪ
    0.24
     болÑĮÑĪой
    0.24
     знаÑĩиÑĤелÑĮно
    0.24
     ÑģилÑĮ
    0.24
     ÑģилÑĮно
    0.23
    Activations Density 0.053%

    No Known Activations