© 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. 7620
    Prev
    Next
    INDEX
    Explanations

    phrases related to compensation or making up for losses

    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
    ungle
    -0.14
    aliz
    -0.14
    ollo
    -0.14
    respons
    -0.14
    iba
    -0.14
    fur
    -0.14
    esper
    -0.14
    _shutdown
    -0.13
    ograms
    -0.13
    stants
    -0.13
    POSITIVE LOGITS
     lost
    0.31
     compensate
    0.27
     Lost
    0.27
    Lost
    0.25
    lost
    0.25
     compens
    0.24
    _lost
    0.23
     compensation
    0.20
     deficiency
    0.19
    å¼¥
    0.19
    Activations Density 0.016%

    No Known Activations