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. 25-LLAMASCOPE-RES-32K
    6. 18179
    Prev
    Next
    INDEX
    Explanations

    references to economic disparity and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplayer
    -0.16
    arlo
    -0.15
    ulp
    -0.14
     ValueEventListener
    -0.14
    zell
    -0.13
     ê°Ŀ
    -0.13
     accommodating
    -0.12
    ackle
    -0.12
    UniformLocation
    -0.12
    assis
    -0.12
    POSITIVE LOGITS
     receive
    0.81
     receives
    0.74
     Receive
    0.68
    receive
    0.68
     receiving
    0.66
    Receive
    0.64
     received
    0.59
     RECEIVE
    0.55
    rece
    0.55
     Rece
    0.55
    Activations Density 0.215%

    No Known Activations