© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 19-LLAMASCOPE-RES-32K
    6. 25588
    Prev
    Next
    INDEX
    Explanations

    phrases related to proposals and statements that generate controversy

    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
    ibName
    -0.17
    ÙħÙĨ
    -0.16
    ideographic
    -0.15
    eturn
    -0.15
     sitios
    -0.14
    à¹Ģห
    -0.14
     nhá»Ŀ
    -0.14
     massaggi
    -0.14
    orna
    -0.14
    ICIENT
    -0.14
    POSITIVE LOGITS
     controversial
    0.30
     causing
    0.28
     cause
    0.27
     controversy
    0.26
     causes
    0.24
    å¼ķ
    0.23
     polar
    0.22
     Causes
    0.20
     caused
    0.20
     raising
    0.20
    Activations Density 0.302%

    No Known Activations