© 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. 2-LLAMASCOPE-RES-32K
    11. 16727
    Prev
    Next
    INDEX
    Explanations

    the word "Pe" which likely indicates a focus on mentions of "Peter" or related names or references

    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
    atan
    -0.14
    ázi
    -0.14
    acent
    -0.14
    UMB
    -0.14
    eper
    -0.14
    pon
    -0.13
    yme
    -0.13
    antha
    -0.13
    UPER
    -0.13
    umb
    -0.13
    POSITIVE LOGITS
    igi
    0.18
    isu
    0.17
    ihan
    0.16
    opak
    0.15
    еÑĢаÑĤÑĥ
    0.15
    zman
    0.14
    imar
    0.14
    ãĥ©ãĥĥãĤ¯
    0.14
    aldi
    0.14
    bilt
    0.14
    Activations Density 0.005%

    No Known Activations