© 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. 28-LLAMASCOPE-RES-32K
    11. 22800
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ata
    -0.13
    aco
    -0.13
    ê°Ģì§Ģ
    -0.13
    [email
    -0.13
     Cub
    -0.13
    hti
    -0.13
    оÑĢÑĥ
    -0.13
    ÑĥÑĢÑĥ
    -0.12
    .cn
    -0.12
    èĨ
    -0.12
    POSITIVE LOGITS
     tags
    0.42
     Tags
    0.41
    Labels
    0.36
    Tags
    0.34
     Labels
    0.32
    tags
    0.31
    TAG
    0.31
    âĨIJ
    0.31
    .Tags
    0.30
     source
    0.30
    Activations Density 0.822%

    No Known Activations