© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 11-LLAMASCOPE-RES-32K
    11. 30860
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to safety and suitability in usage contexts

    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
    ÑĤоÑĢа
    -0.15
    antic
    -0.14
     Inherits
    -0.14
    AMESPACE
    -0.13
    Occurred
    -0.13
    ema
    -0.13
    ients
    -0.13
    avar
    -0.13
    Ä°L
    -0.13
     Secret
    -0.13
    POSITIVE LOGITS
     safety
    0.24
    afety
    0.23
    å®īåħ¨
    0.20
    Safety
    0.19
     Safety
    0.19
    Unsafe
    0.19
     safely
    0.19
     безопаÑģ
    0.18
    -safe
    0.17
    agi
    0.16
    Activations Density 0.186%

    No Known Activations