© 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. 19-LLAMASCOPE-RES-32K
    11. 5615
    Prev
    Next
    INDEX
    Explanations

    phrases related to individual responsibility and awareness in decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ùng
    -0.15
    ReadOnly
    -0.15
    iegel
    -0.14
    ÑĤик
    -0.14
    edar
    -0.14
    ants
    -0.13
    .must
    -0.13
    IGHL
    -0.13
    iffe
    -0.13
     ReadOnly
    -0.13
    POSITIVE LOGITS
     nicht
    0.46
    ä¸įä¼ļ
    0.45
     not
    0.44
    ä¸įæĺ¯
    0.42
     niet
    0.42
     não
    0.41
     không
    0.40
     не
    0.40
     neither
    0.38
     doesn
    0.38
    Activations Density 0.360%

    No Known Activations