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. 16-LLAMASCOPE-RES-32K
    6. 1736
    Prev
    Next
    INDEX
    Explanations

    geographical locations and related administrative changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tampa
    -0.23
     Tacoma
    -0.20
     Colombian
    -0.20
     Seattle
    -0.20
     Columbia
    -0.19
     Kuala
    -0.19
     Florida
    -0.18
     Jacksonville
    -0.18
     Malaysian
    -0.18
    .Azure
    -0.18
    POSITIVE LOGITS
     Nebraska
    0.33
     Omaha
    0.30
     Vermont
    0.23
     Punjab
    0.21
    braska
    0.21
    .liferay
    0.19
     Burlington
    0.19
    neau
    0.18
     Nielsen
    0.18
    strup
    0.17
    Activations Density 0.193%

    No Known Activations