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. 23974
    Prev
    Next
    INDEX
    Explanations

    variations of the phrase "as soon as" or similar expressions indicating urgency or timing

    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
     as
    -0.20
     als
    -0.19
    bindung
    -0.17
    eous
    -0.15
     как
    -0.15
    asca
    -0.15
    że
    -0.14
    ield
    -0.14
    thes
    -0.14
    addtogroup
    -0.14
    POSITIVE LOGITS
     follows
    0.39
    cert
    0.33
    cribed
    0.32
     opposed
    0.31
    sembl
    0.31
    paragus
    0.30
    cribing
    0.28
    cribe
    0.27
     soon
    0.26
    sembles
    0.25
    Activations Density 0.402%

    No Known Activations