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. 31-LLAMASCOPE-RES-32K
    6. 6775
    Prev
    Next
    INDEX
    Explanations

    names and relationships of individuals involved in obituaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freddy
    -0.20
     Edwin
    -0.19
     Jr
    -0.18
     Randy
    -0.18
     Andy
    -0.18
     Kevin
    -0.18
    jr
    -0.18
     William
    -0.18
     Jimmy
    -0.17
     Tommy
    -0.17
    POSITIVE LOGITS
     Marie
    0.46
    Anne
    0.42
     Anne
    0.42
     Louise
    0.41
    Ann
    0.39
     Ann
    0.36
    -Mar
    0.36
     Elizabeth
    0.36
    Jane
    0.35
    Elizabeth
    0.35
    Activations Density 0.248%

    No Known Activations