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. 30-LLAMASCOPE-RES-32K
    6. 16640
    Prev
    Next
    INDEX
    Explanations

    financial misconduct and legal challenges within the banking sector

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tright
    -0.15
    åİĤ
    -0.15
     gast
    -0.15
    pta
    -0.15
    ugin
    -0.15
    kem
    -0.14
    lections
    -0.14
    trand
    -0.14
    ardown
    -0.14
    ouser
    -0.14
    POSITIVE LOGITS
     bonuses
    0.25
     Wall
    0.24
     bonus
    0.23
     SEC
    0.23
     Leh
    0.22
     LIB
    0.21
     Bonus
    0.21
     SAC
    0.21
     Bear
    0.20
     Merrill
    0.20
    Activations Density 0.035%

    No Known Activations