INDEX

Explanations

occurrences of specific types of words or phrases in a mixture of languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

alling

-0.17

redi

-0.15

ALIGN

-0.14

ofilm

-0.14

 ragaz

-0.14

auty

-0.14

 Ð¿Ð¾ÑĤÑĢÐ°Ð¿

-0.14

elib

-0.14

èĢĹ

-0.14

ulent

-0.14

POSITIVE LOGITS

 penn

0.16

.sdk

0.16

 Glock

0.15

iterations

0.15

Pit

0.15

 truncate

0.15

MSN

0.15

gle

0.15

meric

0.14

 unarmed

0.14

Activations Density 0.025%

occurrences of specific types of words or phrases in a mixture of languages

No Comments

No Known Activations