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. 23-LLAMASCOPE-RES-32K
    6. 28207
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a living or earning income

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gili
    -0.18
    utor
    -0.15
    uzzi
    -0.15
    hind
    -0.15
     заклад
    -0.14
    ŀæĢ§
    -0.14
    .RES
    -0.14
    Accessor
    -0.14
     Lansing
    -0.14
    poon
    -0.14
    POSITIVE LOGITS
     living
    0.68
    living
    0.60
     Living
    0.57
    Living
    0.55
     liv
    0.41
    liv
    0.36
     Liv
    0.35
     livelihood
    0.35
     Livingston
    0.34
     sá»ijng
    0.30
    Activations Density 0.036%

    No Known Activations