© 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. 21-LLAMASCOPE-RES-32K
    11. 10595
    Prev
    Next
    INDEX
    Explanations

    phrases related to behavioral change and modification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esty
    -0.18
    Argb
    -0.16
    levance
    -0.14
    ÅĻez
    -0.14
    inding
    -0.14
    offee
    -0.14
    orget
    -0.14
    à¸Ńà¸ĩà¸Īาà¸ģ
    -0.14
    metry
    -0.14
    eka
    -0.13
    POSITIVE LOGITS
     behavior
    0.58
     behaviour
    0.52
     behaviors
    0.50
    è¡Į为
    0.48
     Behavior
    0.47
     habits
    0.46
     actions
    0.43
     behaviours
    0.42
    behavior
    0.42
     повед
    0.38
    Activations Density 0.340%

    No Known Activations