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. 21602
    Prev
    Next
    INDEX
    Explanations

    references to the concept of time and temporal relationships

    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
    wc
    -0.21
    _time
    -0.20
    name
    -0.19
    weg
    -0.19
    TimeStamp
    -0.18
     timed
    -0.17
    (es
    -0.17
     timing
    -0.17
    reg
    -0.16
    istine
    -0.16
    POSITIVE LOGITS
    frames
    0.25
    åĢĻ
    0.24
    othy
    0.24
    piece
    0.23
    punkt
    0.23
    åĪ»
    0.22
    pieces
    0.22
    keeper
    0.21
     frame
    0.20
    lessly
    0.20
    Activations Density 0.241%

    No Known Activations