© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 10239
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional expression and the complexity of feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icos
    -0.15
    icerca
    -0.13
    omentum
    -0.13
    Ä±ÅŁÄ±k
    -0.12
    agnet
    -0.12
    avit
    -0.12
    uhn
    -0.12
    astery
    -0.12
    reiben
    -0.12
     democrat
    -0.12
    POSITIVE LOGITS
     emotion
    0.44
     emotions
    0.44
    emotion
    0.39
     sadness
    0.38
     emotional
    0.38
     affect
    0.35
     Emotional
    0.34
     emot
    0.34
     Em
    0.33
     emoc
    0.32
    Activations Density 0.043%

    No Known Activations