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. 13065
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "check" and its variations within a document

    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
    ityEngine
    -0.16
    alez
    -0.15
    phy
    -0.15
    chap
    -0.15
    serter
    -0.15
    _testing
    -0.15
    teenth
    -0.14
    thest
    -0.14
    DBG
    -0.14
    ichert
    -0.14
    POSITIVE LOGITS
    ered
    0.32
    weigh
    0.24
    mate
    0.22
    lists
    0.22
    mark
    0.21
    SelfPermission
    0.18
    ovacÃŃ
    0.18
    icle
    0.17
    ride
    0.17
    points
    0.17
    Activations Density 0.055%

    No Known Activations