© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 21122
    Prev
    Next
    INDEX
    Explanations

    mentions of years and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olan
    -0.17
    owitz
    -0.16
    oba
    -0.14
    aker
    -0.14
     fold
    -0.14
    seg
    -0.14
     Morgan
    -0.13
    edi
    -0.13
    bose
    -0.13
     tro
    -0.13
    POSITIVE LOGITS
     ÙħÛĮÙĦادÛĮ
    0.19
     Tavern
    0.16
    å¹´
    0.15
    MMdd
    0.15
    .getFullYear
    0.15
    ubat
    0.15
    vale
    0.14
    adiens
    0.14
    ÙĬÙĦاد
    0.14
    achment
    0.14
    Activations Density 0.082%

    No Known Activations