INDEX

Explanations

the word "and" at various frequencies in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oko

-0.19

iko

-0.18

ivo

-0.16

itz

-0.15

oom

-0.15

ogue

-0.14

Ã¼k

-0.14

kh

-0.14

ohn

-0.14

omas

-0.14

POSITIVE LOGITS

alten

0.16

ackbar

0.16

igest

0.15

 Doug

0.15

igure

0.15

EMPLARY

0.14

acias

0.14

odzi

0.14

 misd

0.14

atk

0.14

Activations Density 0.020%

the word "and" at various frequencies in the text

No Comments

No Known Activations