© 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. 13-LLAMASCOPE-RES-32K
    11. 25813
    Prev
    Next
    INDEX
    Explanations

    actions related to maintaining balance and moderation in various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥ½
    -0.18
    erville
    -0.16
     correctly
    -0.16
    еÑı
    -0.15
    èĥ½å¤Ł
    -0.15
    aille
    -0.15
     frequ
    -0.14
    rys
    -0.14
    çĦ¶
    -0.14
    urma
    -0.13
    POSITIVE LOGITS
     anytime
    0.27
    ัà¸Ļà¹Ħà¸Ķ
    0.20
    à¹Ħà¸Ķ
    0.20
     easily
    0.20
     anywhere
    0.19
     à¹Ħà¸Ķ
    0.18
     feas
    0.17
    opies
    0.16
     Saf
    0.16
    à¹Įà¹Ħà¸Ķ
    0.16
    Activations Density 0.890%

    No Known Activations