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. 29-LLAMASCOPE-RES-32K
    6. 3335
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "bre" and its variations, indicating a focus on prefix or root forms associated with the concept of breath or breathing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rr
    -0.17
     inactive
    -0.16
    ror
    -0.16
    row
    -0.15
    CT
    -0.15
    m
    -0.14
    overs
    -0.14
    dam
    -0.14
    cents
    -0.14
     Middleton
    -0.14
    POSITIVE LOGITS
     bre
    0.24
    athing
    0.23
    xit
    0.22
    itbart
    0.22
    thren
    0.22
    autiful
    0.22
    -bre
    0.21
    onna
    0.21
    aching
    0.20
     Bre
    0.20
    Activations Density 0.008%

    No Known Activations