© 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. 26-LLAMASCOPE-RES-32K
    11. 31121
    Prev
    Next
    INDEX
    Explanations

    instances of the word "name" and variations related to identification or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     own
    -0.42
     Own
    -0.38
    Own
    -0.35
    own
    -0.33
    _own
    -0.32
     OWN
    -0.30
     próp
    -0.28
    èĩªå·±çļĦ
    -0.26
    alone
    -0.26
    OWN
    -0.26
    POSITIVE LOGITS
     zich
    0.28
     myself
    0.27
     siÄĻ
    0.25
     sich
    0.25
     yourself
    0.25
     ÑģебÑı
    0.24
     ourselves
    0.24
     himself
    0.23
     Ñģебе
    0.22
     oneself
    0.21
    Activations Density 0.106%

    No Known Activations