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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 7-LLAMASCOPE-RES-32K
    11. 15921
    Prev
    Next
    INDEX
    Explanations

    elements that indicate introspection and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'gc
    -0.16
    hap
    -0.16
    uki
    -0.16
     congr
    -0.14
    ï¼Ń
    -0.14
     Rac
    -0.14
    ä»Ģ
    -0.14
    occo
    -0.14
    å¼
    -0.14
    sburg
    -0.14
    POSITIVE LOGITS
    åĩ
    0.16
    581
    0.14
    eln
    0.14
    ç¢İ
    0.14
    fft
    0.13
    ctor
    0.13
    ãģıãģł
    0.13
    399
    0.13
    ophil
    0.13
     strav
    0.13
    Activations Density 0.336%

    No Known Activations