© 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. 1798
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments related to interpersonal relationships

    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
     tah
    -0.16
     whats
    -0.14
    ewhat
    -0.14
    UPDATED
    -0.13
    olla
    -0.13
    añ
    -0.13
    858
    -0.13
    orting
    -0.13
    éłĤ
    -0.13
     tod
    -0.13
    POSITIVE LOGITS
     none
    0.17
     basically
    0.15
    éľ
    0.15
    TTY
    0.15
    none
    0.15
     sonunda
    0.15
    اÙĨÙĩ
    0.15
     originally
    0.15
     during
    0.15
     nobody
    0.15
    Activations Density 0.499%

    No Known Activations