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. 2-LLAMASCOPE-RES-32K
    6. 25629
    Prev
    Next
    INDEX
    Explanations

    variations of the word "shut."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.19
    herits
    -0.15
    alem
    -0.15
    ัวร
    -0.14
    cope
    -0.14
    'gc
    -0.14
    osate
    -0.14
    िण
    -0.14
    hill
    -0.14
    ceptions
    -0.14
    POSITIVE LOGITS
    -up
    0.18
     otherwise
    0.17
    vably
    0.16
    átek
    0.16
     du
    0.15
    BS
    0.15
    Ð¡Ðł
    0.14
    allah
    0.14
    -off
    0.14
    abble
    0.14
    Activations Density 0.010%

    No Known Activations