INDEX

Explanations

occurrences of the word "one" 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

essler

-0.17

ernet

-0.16

enberg

-0.15

rt

-0.15

anzi

-0.14

ores

-0.14

ocket

-0.14

ãĥ¥ãĥ¼

-0.14

 Stand

-0.13

utenberg

-0.13

POSITIVE LOGITS

ntp

0.15

inox

0.14

utow

0.14

ÑģÐ¾Ðº

0.14

Ð»Ð°Ð²Ð°

0.14

ä¸²

0.13

çħ

0.13

Ú¯Ø§ÙĩÛĮ

0.13

/editor

0.13

dbuf

0.13

Activations Density 0.262%

occurrences of the word "one" in various contexts

No Comments

No Known Activations