© 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. 22-LLAMASCOPE-RES-32K
    11. 18938
    Prev
    Next
    INDEX
    Explanations

    terms related to diversity and variation, particularly in social and biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampion
    -0.17
    ICODE
    -0.16
     оÑħ
    -0.16
    otch
    -0.16
    spir
    -0.15
    imore
    -0.15
     пÑĢоÑĩ
    -0.15
    tein
    -0.15
    icina
    -0.15
    oleÄį
    -0.15
    POSITIVE LOGITS
    ogeneity
    0.22
    ogeneous
    0.21
    olog
    0.18
    å¼Ĥ
    0.18
    gene
    0.17
     heter
    0.16
    ozy
    0.16
    oken
    0.15
    aux
    0.15
    uhan
    0.15
    Activations Density 0.008%

    No Known Activations