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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 25365
    Prev
    Next
    INDEX
    Explanations

    references to the term "Bharti" or its variations, indicating a focus on entities related to that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achs
    -0.22
    iciel
    -0.19
    evice
    -0.17
    eners
    -0.16
    ea
    -0.15
    aths
    -0.15
    ehir
    -0.15
    ureau
    -0.15
    apan
    -0.15
    paren
    -0.15
    POSITIVE LOGITS
    ذا
    0.15
    ant
    0.14
    illy
    0.14
    SSIP
    0.14
    uria
    0.14
    armacy
    0.14
    ế
    0.14
    anna
    0.14
    oral
    0.13
    ãģ¾ãģŁ
    0.13
    Activations Density 0.015%

    No Known Activations