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. 20-LLAMASCOPE-RES-32K
    6. 23908
    Prev
    Next
    INDEX
    Explanations

    words related to sadness and tragedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    727
    -0.16
    lify
    -0.15
     Nightmare
    -0.15
    plevel
    -0.15
    onsense
    -0.14
    meer
    -0.14
    iÄĻ
    -0.14
    ERY
    -0.14
     Dorm
    -0.13
    ItemClick
    -0.13
    POSITIVE LOGITS
    dest
    0.31
    omas
    0.26
    hana
    0.23
    istic
    0.21
    uce
    0.18
    istically
    0.17
    fully
    0.17
    ened
    0.17
    hus
    0.16
    ноп
    0.16
    Activations Density 0.015%

    No Known Activations