© 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. 30196
    Prev
    Next
    INDEX
    Explanations

    concepts related to relationships and the dynamics of multiple parties involved in agreements

    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
    enders
    -0.13
    ongan
    -0.12
    Almost
    -0.12
    ottes
    -0.12
    -Za
    -0.12
    licative
    -0.12
    ennon
    -0.12
    \grid
    -0.12
     Incontri
    -0.12
    oust
    -0.12
    POSITIVE LOGITS
     multiple
    1.03
    multiple
    0.90
     Multiple
    0.87
    Multiple
    0.82
    _multiple
    0.71
    å¤ļ
    0.70
    ultiple
    0.67
     å¤ļ
    0.56
     several
    0.56
     multiples
    0.52
    Activations Density 0.608%

    No Known Activations