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. 31-LLAMASCOPE-RES-32K
    6. 30858
    Prev
    Next
    INDEX
    Explanations

    phrases that challenge stereotypes associated with luxury and consumerism

    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
    .updateDynamic
    -0.13
    onium
    -0.13
    unik
    -0.13
    kovÄĽ
    -0.13
    νοÏį
    -0.13
    unfold
    -0.13
    кÑĢеÑĤ
    -0.13
    tml
    -0.13
    AXB
    -0.12
    arta
    -0.12
    POSITIVE LOGITS
     associations
    0.46
     association
    0.46
     associ
    0.43
     associate
    0.43
     assoc
    0.41
     associated
    0.40
     immediately
    0.39
    association
    0.39
     asoci
    0.38
    associated
    0.38
    Activations Density 0.182%

    No Known Activations