© 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. 30-LLAMASCOPE-RES-32K
    11. 3940
    Prev
    Next
    INDEX
    Explanations

    elements related to music genres and cultural references, particularly within the hip hop and drill scenes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иÑĩеÑģÑĤво
    -0.28
     erste
    -0.27
    die
    -0.27
     gute
    -0.26
     neue
    -0.26
     andere
    -0.26
     weitere
    -0.25
     die
    -0.25
     дÑĢÑĥгие
    -0.24
     seine
    -0.24
    POSITIVE LOGITS
    owych
    0.31
    нÑĭÑħ
    0.29
    аннÑĭÑħ
    0.28
    алÑĮнÑĭÑħ
    0.27
    ÑģкиÑħ
    0.27
    еннÑĭÑħ
    0.27
    овÑĭÑħ
    0.27
    ÑİÑīиÑħ
    0.26
    киÑħ
    0.25
    ÑĪиÑħ
    0.25
    Activations Density 0.093%

    No Known Activations