© 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. 18-LLAMASCOPE-RES-32K
    11. 3061
    Prev
    Next
    INDEX
    Explanations

    phrases describing the actions and characteristics of certain groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.37
     its
    -0.24
     Its
    -0.19
    Its
    -0.18
    eme
    -0.16
     à¤īसà¤ķ
    -0.16
    ara
    -0.16
    åıĬåħ¶
    -0.16
     kendini
    -0.15
     ÙĨÙģسÙĩ
    -0.15
    POSITIVE LOGITS
     themselves
    0.34
     selves
    0.20
    /we
    0.18
    ÅĽmy
    0.17
     respectively
    0.17
     lượt
    0.17
    re
    0.17
    ’re
    0.16
    umber
    0.15
    atical
    0.15
    Activations Density 0.377%

    No Known Activations