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. 23-LLAMASCOPE-RES-32K
    6. 29921
    Prev
    Next
    INDEX
    Explanations

    instances of charitable actions and relief efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dea
    -0.17
     defensively
    -0.14
    .firebaseapp
    -0.14
    ASCADE
    -0.14
    ourd
    -0.14
    eyh
    -0.14
     деÑĢ
    -0.13
    serter
    -0.13
    Descriptors
    -0.13
     поÑıÑģ
    -0.13
    POSITIVE LOGITS
     relief
    0.33
     FEMA
    0.32
     disaster
    0.29
     recovery
    0.29
     Relief
    0.27
     Disaster
    0.27
     rebuilding
    0.26
     debris
    0.26
     Recovery
    0.25
     reconstruction
    0.25
    Activations Density 0.171%

    No Known Activations