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. 30-LLAMASCOPE-RES-32K
    6. 4501
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal accountability and assistance in injury claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongan
    -0.17
    Thirty
    -0.16
     Fifty
    -0.14
    Twenty
    -0.14
     Thirty
    -0.13
     Forty
    -0.13
    -Za
    -0.13
     NÄĽk
    -0.13
    iores
    -0.13
     Sevent
    -0.13
    POSITIVE LOGITS
     several
    1.04
     multiple
    0.77
     numerous
    0.76
     various
    0.73
     Several
    0.72
    Several
    0.69
     many
    0.68
     two
    0.67
     three
    0.66
     plusieurs
    0.63
    Activations Density 1.243%

    No Known Activations