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. 31-LLAMASCOPE-RES-32K
    6. 31177
    Prev
    Next
    INDEX
    Explanations

    phrases related to community events and organizational activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRET
    -0.14
    hetto
    -0.14
    sed
    -0.13
    usher
    -0.13
     convincing
    -0.13
     claimed
    -0.13
     demanded
    -0.13
     convinc
    -0.12
    _totals
    -0.12
    aight
    -0.12
    POSITIVE LOGITS
     pleased
    0.35
     proud
    0.28
     excited
    0.28
     delighted
    0.28
     happy
    0.27
     thrilled
    0.26
     please
    0.24
     Accept
    0.23
     accepting
    0.22
     currently
    0.21
    Activations Density 0.142%

    No Known Activations