Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 31143
    Prev
    Next
    INDEX
    Explanations

    references to historical events and commemorations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ragaz
    -0.12
     ÑģлÑĥÑħ
    -0.12
    .getSeconds
    -0.11
    Nİ
    -0.11
    Ñħи
    -0.11
    ichten
    -0.11
    SessionFactory
    -0.11
    Ú¯ÛĮرÛĮ
    -0.11
    ccount
    -0.10
     zkušen
    -0.10
    POSITIVE LOGITS
     commemor
    0.53
     honoring
    0.51
     commem
    0.51
     commemorate
    0.48
     honor
    0.48
     memorial
    0.47
     honour
    0.47
     honors
    0.46
     tribute
    0.45
     honored
    0.40
    Activations Density 1.681%

    No Known Activations