© 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 EvalsExportsinterp-engineNEWAPI 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. 19218
    Prev
    Next
    INDEX
    Explanations

    references to emotional and physical well-being

    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
    kuk
    -0.14
     oss
    -0.13
     footsteps
    -0.13
    ampa
    -0.13
     blindness
    -0.13
     spontaneously
    -0.13
     Arth
    -0.13
    abin
    -0.13
     Parr
    -0.12
     Giang
    -0.12
    POSITIVE LOGITS
     mental
    0.58
     psychological
    0.49
     psych
    0.48
     Mental
    0.48
    psych
    0.46
    mental
    0.45
    å¿ĥçIJĨ
    0.45
     physical
    0.45
     пÑģиÑħ
    0.43
     emotional
    0.43
    Activations Density 0.517%

    No Known Activations