© 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. 26-LLAMASCOPE-RES-32K
    11. 6273
    Prev
    Next
    INDEX
    Explanations

    patterns of change and stability in relationships and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucz
    -0.15
    apur
    -0.15
    onso
    -0.15
    erto
    -0.14
    uptools
    -0.14
    uebas
    -0.14
     ++)
    -0.14
    rita
    -0.13
    ế
    -0.13
    173
    -0.13
    POSITIVE LOGITS
     change
    0.96
    change
    0.85
     Change
    0.82
     changed
    0.82
    -change
    0.81
    Change
    0.79
     changing
    0.78
     changes
    0.77
     CHANGE
    0.75
    _change
    0.74
    Activations Density 0.397%

    No Known Activations