Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 4609
    Prev
    Next
    INDEX
    Explanations

    terms related to parenting guidance and training

    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
    Confirmation
    -0.15
    ancellable
    -0.14
     widow
    -0.14
     comfortably
    -0.14
    è§
    -0.14
    rez
    -0.14
     comprom
    -0.14
     ske
    -0.14
    .portal
    -0.13
    orgh
    -0.13
    POSITIVE LOGITS
     discipline
    0.44
     discipl
    0.41
     disciplinary
    0.40
     punishment
    0.37
     Discipline
    0.37
     punishments
    0.36
     spanking
    0.34
     Pun
    0.30
     span
    0.28
     punish
    0.28
    Activations Density 0.201%

    No Known Activations