INDEX

Explanations

the indefinite article "a" or "an" 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

anta

-0.15

à¤¾à¤¯à¤¨

-0.14

onga

-0.14

NSE

-0.14

angu

-0.14

enson

-0.14

bung

-0.13

 Campos

-0.13

erce

-0.13

 DefaultValue

-0.13

POSITIVE LOGITS

adle

0.17

.k

0.16

,:,

0.16

 Miles

0.15

Kro

0.15

walker

0.15

ienes

0.14

atre

0.14

hol

0.14

omp

0.14

Activations Density 0.040%

the indefinite article "a" or "an" in various contexts

No Comments

No Known Activations