© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 7314
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yle
    -0.18
    éric
    -0.15
    INGLE
    -0.15
    amina
    -0.15
    ournals
    -0.14
    ayne
    -0.14
    okie
    -0.14
     baÅŁÄ±na
    -0.14
    aiser
    -0.14
    aders
    -0.14
    POSITIVE LOGITS
     friend
    0.78
     friends
    0.74
    æľĭåıĭ
    0.58
     Friend
    0.56
    friend
    0.54
    friends
    0.52
     Friends
    0.51
     FRIEND
    0.50
    Friend
    0.50
    Friends
    0.47
    Activations Density 0.388%

    No Known Activations