© 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. 30-LLAMASCOPE-RES-32K
    11. 19976
    Prev
    Next
    INDEX
    Explanations

    names and titles, particularly in a context related to adult content or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -0.31
     Then
    -0.28
    then
    -0.24
    Then
    -0.22
     THEN
    -0.20
     puis
    -0.20
     entonces
    -0.18
     então
    -0.17
     dann
    -0.17
    THEN
    -0.17
    POSITIVE LOGITS
    aaS
    0.17
    ¶Į
    0.15
    REAK
    0.14
    ÃĹ↵↵
    0.14
     Canter
    0.14
    kommen
    0.14
    нÑĸвеÑĢ
    0.14
    ãĥ³ãĥĶ
    0.13
     Fucking
    0.13
    ãģ¾ãģ¾
    0.13
    Activations Density 0.020%

    No Known Activations