INDEX

Explanations

references to paintings and artwork

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

etric

-0.16

.nlm

-0.16

oco

-0.15

aland

-0.15

 extr

-0.15

engu

-0.14

 infix

-0.14

olec

-0.14

Ì£

-0.14

POSITIVE LOGITS

resco

0.17

fad

0.15

(predicate

0.14

fal

0.14

Ãło

0.14

æ¢

0.14

Ø±ÙĪØ¯

0.14

 Ludwig

0.14

AKER

0.14

zan

0.14

Activations Density 0.002%

references to paintings and artwork

No Comments

No Known Activations