© 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. 21-LLAMASCOPE-RES-32K
    11. 15238
    Prev
    Next
    INDEX
    Explanations

    phrases related to discipline and training, particularly in the context of pets and child-rearing

    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
    chw
    -0.16
    üre
    -0.15
     Bour
    -0.14
    ?url
    -0.14
     comprom
    -0.14
    irus
    -0.14
    #
    -0.14
    ari
    -0.14
     widow
    -0.14
    utter
    -0.13
    POSITIVE LOGITS
     discipl
    0.36
     discipline
    0.34
     disciplinary
    0.32
     spanking
    0.31
     Discipline
    0.30
     punishment
    0.29
     punishments
    0.29
     Pun
    0.24
    disciplinary
    0.23
     disciplines
    0.23
    Activations Density 0.239%

    No Known Activations