© 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. 25-LLAMASCOPE-RES-32K
    11. 11053
    Prev
    Next
    INDEX
    Explanations

    references to treaties and legal documents concerning individual rights and protections

    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
    izi
    -0.15
    ç
    -0.14
    gs
    -0.14
    pp
    -0.14
    ough
    -0.13
    oved
    -0.13
    eners
    -0.13
     Tabs
    -0.13
    ires
    -0.13
    ahoma
    -0.13
    POSITIVE LOGITS
    ibel
    0.19
     White
    0.19
     fate
    0.17
     fur
    0.16
     question
    0.16
     reaction
    0.16
     chair
    0.16
    timing
    0.15
     chairman
    0.15
    eyen
    0.15
    Activations Density 0.126%

    No Known Activations