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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 3989
    Prev
    Next
    INDEX
    Explanations

    references to technical troubleshooting and issues related to printer functionality and game design mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imper
    -0.16
    eka
    -0.16
    onic
    -0.16
    raid
    -0.14
    iese
    -0.14
    çļĦæīĭ
    -0.14
     centr
    -0.14
     Sail
    -0.13
    erna
    -0.13
    ån
    -0.13
    POSITIVE LOGITS
    gni
    0.17
    uffman
    0.15
    atura
    0.15
    WithValue
    0.14
    avan
    0.14
    æ´¾
    0.14
    .yy
    0.14
    #aa
    0.14
    utow
    0.14
    _ASYNC
    0.13
    Activations Density 0.091%

    No Known Activations