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. 24-LLAMASCOPE-RES-32K
    6. 21136
    Prev
    Next
    INDEX
    Explanations

    mentions of fees and charges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.19
    pin
    -0.18
    aneously
    -0.18
    nen
    -0.16
    specific
    -0.16
    maal
    -0.16
    weit
    -0.15
    net
    -0.15
    ød
    -0.15
    enment
    -0.15
    POSITIVE LOGITS
    -paying
    0.24
     charged
    0.23
     structure
    0.22
     paid
    0.22
     Structure
    0.21
     structures
    0.20
     schedule
    0.19
    -paid
    0.19
    _paid
    0.19
    ble
    0.19
    Activations Density 0.029%

    No Known Activations