© 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. 28-LLAMASCOPE-RES-32K
    6. 20616
    Prev
    Next
    INDEX
    Explanations

    terms related to cooperation and cooperative activities

    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
    space
    -0.18
    gie
    -0.18
    spe
    -0.16
     cooperating
    -0.15
     cooperative
    -0.15
    itesse
    -0.15
    gew
    -0.15
       
    -0.15
     còn
    -0.15
    Coeff
    -0.14
    POSITIVE LOGITS
    mans
    0.20
    atives
    0.18
    stown
    0.18
    ating
    0.17
    atively
    0.17
    ider
    0.17
    ativa
    0.17
    portunity
    0.17
    atings
    0.17
    esh
    0.17
    Activations Density 0.011%

    No Known Activations