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. 11-LLAMASCOPE-RES-32K
    6. 18436
    Prev
    Next
    INDEX
    Explanations

    phrases and discussions around effort, music production, and the experiences of individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghi
    -0.16
    overs
    -0.16
    1
    -0.15
    urre
    -0.15
    owell
    -0.15
     states
    -0.15
     slack
    -0.15
     debtor
    -0.14
    x
    -0.14
    top
    -0.14
    POSITIVE LOGITS
    ÙĪÛĮÙĩ
    0.16
    rar
    0.15
    ollo
    0.15
    िण
    0.15
    occo
    0.15
    пов
    0.15
     EXEMPLARY
    0.15
    .createComponent
    0.14
    dden
    0.14
    APTER
    0.14
    Activations Density 0.603%

    No Known Activations