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. 16337
    Prev
    Next
    INDEX
    Explanations

    punctuation, particularly quotation marks and commas

    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
    ACHER
    -0.14
     اÙĬÙĨ
    -0.14
     accordion
    -0.14
    anch
    -0.14
    ati
    -0.14
    çĨĬ
    -0.13
    διά
    -0.13
    ì°°
    -0.13
    ienes
    -0.13
     ActionTypes
    -0.13
    POSITIVE LOGITS
    ozÃŃ
    0.17
    bero
    0.16
    ovsky
    0.16
    åĪij
    0.15
    ream
    0.15
     apprent
    0.15
    вÑĸÑĤ
    0.14
    wire
    0.14
    EdgeInsets
    0.14
    Locale
    0.14
    Activations Density 0.185%

    No Known Activations