© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15948
    Prev
    Next
    INDEX
    Explanations

    phrases regarding human actions and interactions

    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
    inho
    -0.16
    ama
    -0.14
    Äįast
    -0.14
    ãģ¤ãģ¶
    -0.14
     ÑĤебÑı
    -0.13
    ssp
    -0.13
     senin
    -0.13
    ãĢĤä½ł
    -0.13
     ÑĤебе
    -0.13
     hạ
    -0.13
    POSITIVE LOGITS
     Mr
    1.35
    Mr
    1.19
     Ms
    0.97
     mr
    0.90
     Mrs
    0.81
    Ms
    0.79
    mr
    0.68
    _mr
    0.68
     MR
    0.66
    Mrs
    0.66
    Activations Density 0.366%

    No Known Activations