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. 9-LLAMASCOPE-RES-32K
    6. 5309
    Prev
    Next
    INDEX
    Explanations

    references to royal succession and heirship

    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
     resourceName
    -0.16
    VISIBLE
    -0.15
    auss
    -0.15
    aise
    -0.15
    usercontent
    -0.14
    apos
    -0.14
    iais
    -0.14
    -ignore
    -0.14
    ebin
    -0.14
    ousse
    -0.14
    POSITIVE LOGITS
    NR
    0.16
    gado
    0.16
     groom
    0.16
    ali
    0.16
    áli
    0.15
    205
    0.14
    ambi
    0.14
    ζη
    0.14
    λη
    0.14
    &R
    0.14
    Activations Density 0.022%

    No Known Activations