© 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. 23-LLAMASCOPE-RES-32K
    11. 2836
    Prev
    Next
    INDEX
    Explanations

    references to New Year's resolutions and personal goal-setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mandatory
    -0.14
    igne
    -0.14
    emma
    -0.14
    ousse
    -0.13
    zu
    -0.13
    yk
    -0.13
    zion
    -0.13
    çĽĸ
    -0.13
    Coordinates
    -0.13
    edin
    -0.13
    POSITIVE LOGITS
     resolutions
    0.46
     resolution
    0.39
    resolution
    0.35
     Resolution
    0.34
    -resolution
    0.32
     resolves
    0.30
    Resolution
    0.30
     resolve
    0.29
     goals
    0.29
     January
    0.29
    Activations Density 0.052%

    No Known Activations