INDEX

Explanations

variations of the word "esh," likely indicating a focus on specific names or terms associated with brands or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

.LENGTH

-0.17

thon

-0.17

auss

-0.15

lij

-0.15

eeper

-0.15

agara

-0.15

å¥Ķ

-0.15

idget

-0.15

orld

-0.15

CKER

-0.15

POSITIVE LOGITS

cent

0.16

entially

0.16

-vous

0.15

iah

0.15

eyh

0.14

war

0.14

uality

0.14

enter

0.14

 Void

0.14

Ð·Ð½Ð°ÑĩÐ°

0.14

Activations Density 0.051%

variations of the word "esh," likely indicating a focus on specific names or terms associated with brands or individuals

No Comments

No Known Activations