© 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. 5-LLAMASCOPE-RES-32K
    11. 18713
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing identity or self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñĭл
    -0.14
    eniable
    -0.14
    ecided
    -0.14
    ddit
    -0.14
    anel
    -0.14
    verages
    -0.14
    تر
    -0.13
    kos
    -0.13
    hn
    -0.13
    lor
    -0.13
    POSITIVE LOGITS
     excess
    0.16
    enant
    0.15
    nature
    0.14
    اسÙĩ
    0.14
    ereum
    0.14
    kem
    0.14
     #__
    0.14
    rám
    0.14
     :";↵
    0.13
     PartialView
    0.13
    Activations Density 0.072%

    No Known Activations