INDEX

Explanations

conjunctions indicating connections or relationships between ideas

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

riad

-0.16

 addCriterion

-0.15

EMPTY

-0.15

ÑĳÑĤ

-0.14

dw

-0.14

ERVED

-0.14

ouri

-0.14

stile

-0.14

declspec

-0.14

.descriptor

-0.14

POSITIVE LOGITS

illery

0.14

 terr

0.14

åĨ³

0.14

æ±º

0.13

 comma

0.13

usters

0.13

letics

0.13

/or

0.13

emouth

0.13

-Sah

0.13

Activations Density 0.054%

conjunctions indicating connections or relationships between ideas

No Known Activations