© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to audio and headphones

    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
     headphones
    -0.20
    atron
    -0.17
    815
    -0.16
     ear
    -0.15
    ubi
    -0.15
    685
    -0.15
    oren
    -0.15
    esium
    -0.14
    uhan
    -0.14
    geist
    -0.14
    POSITIVE LOGITS
     Hands
    0.17
     hands
    0.16
    issan
    0.16
     Voice
    0.16
     Qualcomm
    0.15
    rais
    0.15
     Siri
    0.15
    .UIManager
    0.15
     EQ
    0.15
     voice
    0.15
    Activations Density 0.028%

    No Known Activations