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. 9-LLAMASCOPE-RES-32K
    6. 4084
    Prev
    Next
    INDEX
    Explanations

    places of interest and historical significance

    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
    ACA
    -0.14
    addOn
    -0.14
    ease
    -0.14
     moy
    -0.14
    dux
    -0.14
    tvrt
    -0.14
    imeline
    -0.14
     мÑĭÑĪ
    -0.13
    ɵ
    -0.13
    lak
    -0.13
    POSITIVE LOGITS
    abbage
    0.15
     Mane
    0.14
    teÅŁ
    0.14
     Epid
    0.14
    .foundation
    0.14
    aya
    0.14
     NM
    0.14
    noon
    0.14
    еÑĢб
    0.13
    anlık
    0.13
    Activations Density 0.105%

    No Known Activations