© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and admission of responsibility

    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
    Closure
    -0.17
     Closure
    -0.15
    بÙĪاسطة
    -0.15
    zÃŃ
    -0.14
    abus
    -0.14
    ycz
    -0.14
    FRING
    -0.14
    олÑĮз
    -0.14
    ettel
    -0.14
    OVÃģ
    -0.14
    POSITIVE LOGITS
     admission
    0.84
     admit
    0.81
     admitted
    0.80
     admitting
    0.77
     admits
    0.73
     admissions
    0.73
     Admission
    0.69
     acknowledge
    0.59
     acknowledgement
    0.57
     acknowledgment
    0.56
    Activations Density 0.339%

    No Known Activations