© 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. 18-LLAMASCOPE-RES-32K
    11. 25770
    Prev
    Next
    INDEX
    Explanations

    relationships and dynamics surrounding fidelity and romance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frau
    -0.34
     woman
    -0.32
     vrouw
    -0.30
     wife
    -0.29
    woman
    -0.29
     Woman
    -0.29
    wife
    -0.28
     lady
    -0.28
     wives
    -0.28
    -wife
    -0.27
    POSITIVE LOGITS
     male
    0.38
     males
    0.38
     husbands
    0.37
     boyfriend
    0.37
    çĶ·åŃIJ
    0.34
     husband
    0.33
     guy
    0.33
     masculine
    0.32
     men
    0.32
     handsome
    0.32
    Activations Density 0.547%

    No Known Activations