© 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. 22-LLAMASCOPE-RES-32K
    11. 11454
    Prev
    Next
    INDEX
    Explanations

    references to digital media and gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pto
    -0.18
    AIT
    -0.16
     ÑĢаÑħ
    -0.15
    urovision
    -0.15
    ieber
    -0.15
    udur
    -0.14
    olls
    -0.14
    Ùģت
    -0.14
    Disclosure
    -0.14
    ubat
    -0.14
    POSITIVE LOGITS
     atleast
    0.82
    èĩ³å°ij
    0.71
     least
    0.65
     alespoÅĪ
    0.63
     Least
    0.54
    least
    0.54
     ÑħоÑĤÑı
    0.46
    Least
    0.46
     ØŃداÙĤÙĦ
    0.42
    _least
    0.41
    Activations Density 0.459%

    No Known Activations