© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20699
    Prev
    Next
    INDEX
    Explanations

    phrases indicating obligations or responsibilities in interpersonal relationships

    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
     themselves
    -0.44
     itself
    -0.31
     Their
    -0.21
     their
    -0.19
     himself
    -0.19
    Their
    -0.19
     leurs
    -0.18
     kita
    -0.17
     иÑħ
    -0.16
    ald
    -0.16
    POSITIVE LOGITS
     yourself
    0.76
     yourselves
    0.50
     Yourself
    0.49
     your
    0.40
    your
    0.39
    ä½łçļĦ
    0.34
     можеÑĤе
    0.30
     hebt
    0.27
     ваÑĪ
    0.26
    Your
    0.25
    Activations Density 1.219%

    No Known Activations