INDEX

Explanations

concepts related to perception and reality in a nuanced manner

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ«ãĤ¯

-0.13

indsight

-0.12

.toolbox

-0.11

ÐµÐºÑĥ

-0.11

Ø§Ø³ÛĮ

-0.11

ORITY

-0.11

udad

-0.11

ummings

-0.11

afÃ¼r

-0.11

omid

-0.11

POSITIVE LOGITS

 genuine

0.75

 real

0.73

 actual

0.72

 truly

0.72

 true

0.72

 genuinely

0.70

 actually

0.69

çľŁæŃ£

0.67

 really

0.63

 REAL

0.59

Activations Density 1.109%

concepts related to perception and reality in a nuanced manner

No Comments

No Known Activations