© 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. 20278
    Prev
    Next
    INDEX
    Explanations

    verbs indicating rapid or prompt actions or changes

    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
     finally
    -0.33
    finally
    -0.27
     Finally
    -0.26
    Finally
    -0.26
    ç»Īäºİ
    -0.21
    continued
    -0.21
     continued
    -0.19
    	finally
    -0.19
     eventually
    -0.19
    Lastly
    -0.19
    POSITIVE LOGITS
     chóng
    0.20
     thereafter
    0.18
    aneously
    0.18
    'gc
    0.18
     become
    0.16
     became
    0.15
    chor
    0.15
    forgettable
    0.15
    bec
    0.15
     Forget
    0.15
    Activations Density 0.118%

    No Known Activations