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. 10-LLAMASCOPE-RES-32K
    6. 3842
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to student-related issues and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    884
    -0.17
    atrix
    -0.16
    ixa
    -0.16
    arda
    -0.15
    utas
    -0.15
    ityEngine
    -0.15
    íĦ°
    -0.14
    847
    -0.14
    yna
    -0.13
    PyObject
    -0.13
    POSITIVE LOGITS
    unn
    0.16
    asurer
    0.16
    hsi
    0.16
    errat
    0.15
    živ
    0.15
    ovan
    0.14
    zia
    0.14
    NJ
    0.14
     Fairfax
    0.14
    ÏĥÏĥ
    0.14
    Activations Density 0.028%

    No Known Activations