© 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. 13-LLAMASCOPE-RES-32K
    11. 27020
    Prev
    Next
    INDEX
    Explanations

    actions related to giving or transferring items or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akis
    -0.15
    ely
    -0.15
    ensem
    -0.15
     cork
    -0.15
     plaster
    -0.15
    plier
    -0.14
    egis
    -0.14
    dub
    -0.14
    ombo
    -0.14
    colo
    -0.14
    POSITIVE LOGITS
     kepada
    0.24
    ToDevice
    0.22
     unto
    0.18
    odesk
    0.16
    åĩºåİ»
    0.15
    liner
    0.15
    hiba
    0.15
    oice
    0.15
    ix
    0.14
    ç»Ļ
    0.14
    Activations Density 0.240%

    No Known Activations