Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 28071
    Prev
    Next
    INDEX
    Explanations

    expressions of interest or perception of something as appealing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tera
    -0.15
     ful
    -0.15
     
    -0.15
     Bott
    -0.14
     Pok
    -0.14
    edith
    -0.14
     Thornton
    -0.14
    ÅĻÃŃ
    -0.14
     McCabe
    -0.13
    foon
    -0.13
    POSITIVE LOGITS
     familiar
    0.20
     Fam
    0.16
    ãĥ¼ãĥľ
    0.16
    amiliar
    0.16
    seau
    0.15
    mouth
    0.14
    лим
    0.14
    ë¥ĺ
    0.14
    rait
    0.14
    Sus
    0.14
    Activations Density 0.037%

    No Known Activations