INDEX

Explanations

indefinite articles "a" and "an" used in various contexts

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

 blat

-0.18

Øª

-0.15

sax

-0.15

Sil

-0.14

 designer

-0.14

bos

-0.14

bit

-0.14

itori

-0.14

ushman

-0.14

-0.13

POSITIVE LOGITS

elon

0.16

ÅŁa

0.16

xEE

0.15

odef

0.14

Äįe

0.14

roke

0.14

elman

0.14

tape

0.14

indle

0.14

edeki

0.14

Activations Density 0.044%

indefinite articles "a" and "an" used in various contexts

No Comments

No Known Activations