© 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. 23-LLAMASCOPE-RES-32K
    11. 15453
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment benefits and working conditions

    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
    orna
    -0.16
    ãģĭãĤĬ
    -0.15
    ARING
    -0.15
     Moy
    -0.15
    ypass
    -0.14
    AGMA
    -0.14
    ahoo
    -0.14
    æĶ¶åħ¥
    -0.14
    registr
    -0.14
    İ
    -0.14
    POSITIVE LOGITS
     benefits
    0.52
     Benefits
    0.44
    Benefits
    0.38
     benefit
    0.37
    benef
    0.35
     perks
    0.34
     Benefit
    0.31
     fringe
    0.28
    401
    0.27
     sick
    0.26
    Activations Density 0.106%

    No Known Activations