Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 3070
    Prev
    Next
    INDEX
    Explanations

    instances of moral reasoning and empathy in social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avit
    -0.17
    uelle
    -0.17
    oldt
    -0.16
    zzo
    -0.15
    akan
    -0.15
    rezent
    -0.14
    unga
    -0.14
    icari
    -0.14
    .MaxLength
    -0.14
    lege
    -0.14
    POSITIVE LOGITS
     sympath
    0.25
     Perspective
    0.20
     perspective
    0.20
     Side
    0.19
     sympathy
    0.19
     sided
    0.19
     side
    0.18
     sympathetic
    0.18
     perspectives
    0.18
     symp
    0.17
    Activations Density 0.220%

    No Known Activations