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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30-LLAMASCOPE-RES-32K
    6. 22433
    Prev
    Next
    INDEX
    Explanations

    phrases related to social progress and community welfare initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beans
    -0.15
     voksne
    -0.15
     Russell
    -0.15
     beans
    -0.14
     eldre
    -0.14
    voy
    -0.14
    ãģ£ãģį
    -0.14
    ãĥ³ãĤ¬
    -0.14
    nz
    -0.14
    ãĥ¼ãĥĨãĤ£
    -0.13
    POSITIVE LOGITS
     Swedish
    0.71
     Sweden
    0.69
     Stockholm
    0.65
    Sweden
    0.59
     Svens
    0.58
     stockholm
    0.52
     Lund
    0.45
     Scandin
    0.43
     Nordic
    0.42
     Scandinavian
    0.42
    Activations Density 0.264%

    No Known Activations