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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 20735
    Prev
    Next
    INDEX
    Explanations

    references to fictional narratives and dramas involving characters and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EINA
    -0.16
    steder
    -0.15
    baugh
    -0.15
    cem
    -0.14
    otomy
    -0.14
    uhn
    -0.14
    zel
    -0.14
    mamak
    -0.14
     guarda
    -0.14
    buster
    -0.13
    POSITIVE LOGITS
    736
    0.17
     Patch
    0.14
    735
    0.14
    ackers
    0.14
    inka
    0.14
    ewan
    0.14
    insky
    0.14
    733
    0.14
     Fiction
    0.14
    533
    0.14
    Activations Density 0.102%

    No Known Activations