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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8533
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal identities and roles, particularly those involving professional or social labels

    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
    loor
    -0.16
    irq
    -0.16
    èĨ
    -0.15
    inis
    -0.15
     Backpack
    -0.15
    ift
    -0.14
    hero
    -0.14
    179
    -0.13
    åĤ
    -0.13
    Åijs
    -0.13
    POSITIVE LOGITS
     myself
    0.17
     former
    0.16
     lay
    0.16
    éIJ
    0.16
     pract
    0.15
    .FLAG
    0.15
     someone
    0.15
     Lay
    0.15
     recovering
    0.15
     somebody
    0.14
    Activations Density 0.164%

    No Known Activations