Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-LLAMASCOPE-RES-32K
    6. 6507
    Prev
    Next
    INDEX
    Explanations

    references to nighttime or evening events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ohn
    -0.19
    اÙħØ©
    -0.18
    .scalablytyped
    -0.17
    aggio
    -0.17
    erer
    -0.16
    ckett
    -0.15
    tron
    -0.15
    oeff
    -0.15
    ovit
    -0.15
    hammad
    -0.14
    POSITIVE LOGITS
    clubs
    0.18
    mar
    0.17
    ea
    0.17
    lights
    0.16
    cap
    0.16
     night
    0.16
    -night
    0.16
    aby
    0.15
    /day
    0.15
    night
    0.15
    Activations Density 0.040%

    No Known Activations