© 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. 2-LLAMASCOPE-RES-32K
    11. 7600
    Prev
    Next
    INDEX
    Explanations

    repeated conjunctions and phrases with multiple "and" that suggest a list or accumulation of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OLON
    -0.17
    ÙħاÙħ
    -0.16
    ì¹Ļ
    -0.15
    onn
    -0.15
    ẩy
    -0.15
    aad
    -0.15
    sin
    -0.14
    onne
    -0.14
    arak
    -0.14
    /vnd
    -0.14
    POSITIVE LOGITS
    itis
    0.15
     circulating
    0.15
    zer
    0.14
    opathy
    0.14
    ta
    0.14
     circulation
    0.14
    disp
    0.14
    252
    0.14
    -l
    0.13
    233
    0.13
    Activations Density 0.133%

    No Known Activations