© 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. 20-LLAMASCOPE-RES-32K
    11. 26184
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific individuals or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑģÑĤÑĢÑĥ
    -0.17
    anks
    -0.17
    ADX
    -0.15
    -door
    -0.15
    ropa
    -0.15
     Claw
    -0.14
    esco
    -0.14
    /******/
    -0.14
    782
    -0.14
    جاÙħ
    -0.14
    POSITIVE LOGITS
    quez
    0.24
    à¥įतव
    0.22
    iliki
    0.20
    ques
    0.18
    byt
    0.17
    htar
    0.16
    ervas
    0.15
    éĩı
    0.15
    cul
    0.15
    Ø·ÙĬ
    0.15
    Activations Density 0.022%

    No Known Activations