© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 18896
    Prev
    Next
    INDEX
    Explanations

    technical terms related to radar and signal processing

    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
    .Fat
    -0.15
    .ix
    -0.15
     Transitional
    -0.14
    Acceler
    -0.14
     Peace
    -0.14
     peace
    -0.14
    Peace
    -0.14
     ust
    -0.14
    rzy
    -0.14
    peace
    -0.13
    POSITIVE LOGITS
     retrie
    0.31
     retrieval
    0.29
     Retrie
    0.26
     retrieved
    0.25
     extinction
    0.25
     aeros
    0.25
     retrieves
    0.24
     Aeros
    0.23
     zenith
    0.23
     retrieve
    0.21
    Activations Density 0.047%

    No Known Activations