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. 2531
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "find" along with references to searching or locating items or information

    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
    pto
    -0.16
    Į
    -0.16
    uter
    -0.16
    ailable
    -0.15
    bler
    -0.15
    urance
    -0.15
    CHED
    -0.14
     sensible
    -0.14
    aget
    -0.14
    Ãły
    -0.14
    POSITIVE LOGITS
    NavController
    0.15
     gems
    0.14
     gem
    0.14
     Mun
    0.14
    allen
    0.14
     Schro
    0.14
    ekli
    0.14
    eyin
    0.14
    rowing
    0.14
    tain
    0.13
    Activations Density 0.052%

    No Known Activations