© 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. 9-LLAMASCOPE-RES-32K
    11. 24911
    Prev
    Next
    INDEX
    Explanations

    personal reflections and experiences related to self-identity and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enz
    -0.15
    nez
    -0.15
    ula
    -0.15
    ãĥ¼ãĤ¸
    -0.15
    eny
    -0.15
     rather
    -0.15
    ngr
    -0.14
    usu
    -0.14
     Scho
    -0.14
    ess
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.21
    иÑģлов
    0.16
    prung
    0.16
    icode
    0.15
    ysi
    0.15
     Bender
    0.15
    ostel
    0.15
    ripp
    0.15
    ickt
    0.14
    UMENT
    0.14
    Activations Density 0.284%

    No Known Activations