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. 21-LLAMASCOPE-RES-32K
    6. 16223
    Prev
    Next
    INDEX
    Explanations

    references to a specific brand or product line named "Next Generation" or similar iterations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aghan
    -0.16
    rift
    -0.15
    uten
    -0.15
    ishments
    -0.15
    uluk
    -0.14
    ippi
    -0.14
    defaults
    -0.14
    heit
    -0.14
    esso
    -0.14
    ados
    -0.14
    POSITIVE LOGITS
    -generation
    0.24
    GEN
    0.21
    door
    0.21
     Generation
    0.20
     generation
    0.19
    ernal
    0.19
    generation
    0.18
    ailing
    0.17
    -gen
    0.17
    Gen
    0.16
    Activations Density 0.023%

    No Known Activations