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. 25-LLAMASCOPE-RES-32K
    6. 11138
    Prev
    Next
    INDEX
    Explanations

    various elements of structured data such as code, dates, and specific product names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     punches
    -0.16
    ipa
    -0.15
    Pow
    -0.14
     Punch
    -0.14
    ifer
    -0.14
    odule
    -0.14
     punch
    -0.14
    å¸ķ
    -0.14
    pas
    -0.14
    Payload
    -0.14
    POSITIVE LOGITS
     pet
    1.36
     Pet
    1.34
    Pet
    1.22
    pet
    1.18
     PET
    1.13
     petition
    1.08
    _pet
    1.07
    .pet
    1.05
    PET
    1.03
     pets
    0.99
    Activations Density 0.055%

    No Known Activations