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. 2-LLAMASCOPE-RES-32K
    6. 16152
    Prev
    Next
    INDEX
    Explanations

    references to terraces or terrace-like structures in descriptions of properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaux
    -0.15
    spell
    -0.15
    ment
    -0.15
     Freeman
    -0.14
    len
    -0.14
    nder
    -0.14
    аков
    -0.14
    deaux
    -0.14
    sian
    -0.14
    ogany
    -0.13
    POSITIVE LOGITS
    monkey
    0.17
     Kub
    0.15
    ipar
    0.15
    ington
    0.15
    _Session
    0.14
    Monkey
    0.14
     invent
    0.14
    reta
    0.14
    atched
    0.14
    ceipt
    0.13
    Activations Density 0.013%

    No Known Activations