© 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. 20-LLAMASCOPE-RES-32K
    11. 26604
    Prev
    Next
    INDEX
    Explanations

    varying degrees of self-identification and descriptors related to personal attributes

    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
    oste
    -0.16
    slaught
    -0.15
     nonatomic
    -0.15
    oi
    -0.15
    thora
    -0.15
    locker
    -0.14
    opher
    -0.14
    èĢħçļĦ
    -0.14
    PIX
    -0.14
    ateria
    -0.14
    POSITIVE LOGITS
     victim
    0.19
    verse
    0.19
     part
    0.18
    acional
    0.17
     unto
    0.17
     menace
    0.16
     frequent
    0.16
     victims
    0.16
     disappointment
    0.15
     rarity
    0.15
    Activations Density 0.187%

    No Known Activations