© 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. 22-LLAMASCOPE-RES-32K
    11. 12045
    Prev
    Next
    INDEX
    Explanations

    verbs and actions indicating processes of change or compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ed
    -0.54
    edik
    -0.31
    edn
    -0.28
    edBy
    -0.26
    edir
    -0.22
    edata
    -0.21
    edb
    -0.20
    edu
    -0.20
    lify
    -0.19
    edral
    -0.19
    POSITIVE LOGITS
    ing
    1.10
    ING
    0.64
    ingt
    0.49
    ingen
    0.39
    ingly
    0.36
    ings
    0.35
    ë§ģ
    0.34
    inge
    0.33
    инг
    0.32
    ãĥ³ãĤ°
    0.31
    Activations Density 0.234%

    No Known Activations