© 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. 20-LLAMASCOPE-RES-32K
    11. 12905
    Prev
    Next
    INDEX
    Explanations

    structured data related to technology and algorithms, particularly involving statistical processes and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PPER
    -0.14
     noh
    -0.13
     nedir
    -0.13
     ç±
    -0.13
     norge
    -0.12
    !--
    -0.12
    Âłmi
    -0.12
    大人
    -0.12
    ÂłkW
    -0.12
     mastur
    -0.12
    POSITIVE LOGITS
     addCriterion
    0.13
     daleko
    0.12
    ezier
    0.12
    Ìĥ
    0.12
     vivastreet
    0.11
    raquo
    0.11
     kraje
    0.11
    Unnamed
    0.11
    <|end_of_text|>
    0.11
    -scalable
    0.11
    Activations Density 2.743%

    No Known Activations