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. 22-LLAMASCOPE-RES-32K
    6. 20376
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence or emphasis of a particular subject or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    or
    -0.17
    ure
    -0.15
    &
    -0.15
     Toll
    -0.15
     cac
    -0.15
    -in
    -0.14
    685
    -0.14
     ref
    -0.14
    irk
    -0.14
    apo
    -0.14
    POSITIVE LOGITS
     display
    0.30
     sale
    0.27
    sale
    0.25
     tap
    0.23
    display
    0.23
     offer
    0.22
    Sale
    0.22
    offer
    0.21
    .display
    0.21
     SALE
    0.20
    Activations Density 0.084%

    No Known Activations