© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 28669
    Prev
    Next
    INDEX
    Explanations

    expressions related to community support and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нима
    -0.14
    objectManager
    -0.14
    untime
    -0.13
    лива
    -0.13
     há»į
    -0.12
    μαι
    -0.12
    ẽ
    -0.12
    íķĺìĦ¸ìļĶ
    -0.11
    iginal
    -0.11
    verture
    -0.11
    POSITIVE LOGITS
     our
    0.97
     ourselves
    0.94
     we
    0.94
     ours
    0.84
    æĪij们
    0.84
    æĪijåĢij
    0.81
    æĪij们çļĦ
    0.76
    ï¼ĮæĪij们
    0.70
    our
    0.68
    we
    0.64
    Activations Density 3.375%

    No Known Activations