© 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. 22-LLAMASCOPE-RES-32K
    6. 2918
    Prev
    Next
    INDEX
    Explanations

    expressions of positive subjective experiences

    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
    oman
    -0.15
    agan
    -0.14
    isci
    -0.14
    IVO
    -0.14
    ilog
    -0.13
    .conf
    -0.13
     vo
    -0.13
    sip
    -0.13
    Lights
    -0.13
    upp
    -0.13
    POSITIVE LOGITS
     nice
    0.56
    nice
    0.47
    Nice
    0.47
     Nice
    0.45
     glad
    0.39
     Glad
    0.39
     nic
    0.32
     great
    0.30
     pleasure
    0.28
     nicer
    0.26
    Activations Density 0.204%

    No Known Activations