© 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. 17500
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbial forms in various contexts

    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
    itu
    -0.16
    Ïħ
    -0.16
    ifo
    -0.16
    oller
    -0.15
    ined
    -0.15
    ÑĮ
    -0.15
    à¯į
    -0.14
    ÑĮÑİ
    -0.14
    ìľ¼ë¡ľ
    -0.14
    itore
    -0.14
    POSITIVE LOGITS
    tics
    0.30
    lation
    0.30
    e
    0.29
    sis
    0.28
    ellow
    0.28
    tic
    0.27
    yyyy
    0.27
    ea
    0.26
    yyy
    0.26
    eah
    0.26
    Activations Density 0.067%

    No Known Activations