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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-LLAMASCOPE-RES-32K
    6. 23841
    Prev
    Next
    INDEX
    Explanations

    expressions of physical and emotional exhaustion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utra
    -0.15
    zeÅĦ
    -0.15
    tam
    -0.15
    emouth
    -0.14
    crate
    -0.14
    licer
    -0.14
     affirm
    -0.14
    angi
    -0.14
     summers
    -0.13
    ekl
    -0.13
    POSITIVE LOGITS
     exhaustion
    0.40
     tired
    0.38
     fatigue
    0.38
     exhausted
    0.33
    çĸ²
    0.30
     Exhaust
    0.29
     energy
    0.25
    ç´¯
    0.25
     wear
    0.24
     weary
    0.24
    Activations Density 0.280%

    No Known Activations