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. 6146
    Prev
    Next
    INDEX
    Explanations

    TV show titles and ratings information

    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
    ovÃŃ
    -0.17
     âĹĦ
    -0.15
    Ãłng
    -0.15
    astle
    -0.15
    MESS
    -0.15
    .twig
    -0.14
    anness
    -0.14
    eki
    -0.14
    htm
    -0.14
     tim
    -0.14
    POSITIVE LOGITS
    ASM
    0.17
     traffic
    0.15
     audience
    0.15
     Nielsen
    0.15
     attendance
    0.15
    Ni
    0.15
     audiences
    0.15
     Traffic
    0.15
    ÅĤÄħ
    0.15
    icer
    0.14
    Activations Density 0.077%

    No Known Activations