© 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. 18759
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to significant risks or dangers, particularly in health contexts

    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
    ä¼´
    -0.16
    quan
    -0.16
    IVA
    -0.14
    orris
    -0.14
    Formatting
    -0.14
    ISIBLE
    -0.13
    Ø®ÙĪ
    -0.13
    ãĥ¼ãĤº
    -0.13
     kole
    -0.13
     Antar
    -0.13
    POSITIVE LOGITS
     Ney
    0.18
    uhn
    0.15
     Crosby
    0.15
     Bet
    0.14
    itals
    0.14
     EP
    0.14
    Recognizer
    0.14
     beyond
    0.14
    bet
    0.14
    gart
    0.13
    Activations Density 0.005%

    No Known Activations