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. 28-LLAMASCOPE-RES-32K
    6. 29962
    Prev
    Next
    INDEX
    Explanations

    details related to violent criminal incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fik
    -0.19
     Yard
    -0.15
    imon
    -0.15
    رش
    -0.14
    Yahoo
    -0.14
     Yahoo
    -0.14
    ountains
    -0.13
    λικ
    -0.13
    antlr
    -0.13
    å¾·
    -0.13
    POSITIVE LOGITS
     booking
    0.33
     bond
    0.29
     Booking
    0.28
     booked
    0.28
     bookings
    0.27
    bond
    0.27
     arr
    0.26
    Bond
    0.26
    Booking
    0.26
     Bond
    0.25
    Activations Density 0.061%

    No Known Activations