© 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. 27-LLAMASCOPE-RES-32K
    11. 10944
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "David" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    алеж
    -0.16
    ound
    -0.16
    verter
    -0.14
    ums
    -0.14
    umont
    -0.14
     ÙĪرد
    -0.14
    iffer
    -0.14
    epar
    -0.14
    inkel
    -0.14
    ÑĢование
    -0.14
    POSITIVE LOGITS
     Bowie
    0.25
     Duch
    0.22
     Letter
    0.17
     Crosby
    0.17
    -cross
    0.17
     Mam
    0.17
     Yaz
    0.16
     Byrne
    0.16
    ubby
    0.16
    iants
    0.16
    Activations Density 0.009%

    No Known Activations