© 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. 18-LLAMASCOPE-RES-32K
    6. 1233
    Prev
    Next
    INDEX
    Explanations

    expressions related to expectations and what is deemed appropriate or inappropriate behavior

    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
    TPL
    -0.20
    vap
    -0.16
    ICTURE
    -0.15
    asel
    -0.15
    æ¨
    -0.14
    że
    -0.14
    emy
    -0.14
     запаÑģ
    -0.14
    ondere
    -0.14
    emet
    -0.14
    POSITIVE LOGITS
     shouldn
    0.44
     should
    0.35
    should
    0.35
     ought
    0.34
     Should
    0.32
    Should
    0.32
     SHOULD
    0.27
    .should
    0.26
    åºĶ该
    0.25
     deber
    0.24
    Activations Density 0.153%

    No Known Activations