INDEX

Explanations

repeated references to the word "other."

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

ĵn

-0.17

IBE

-0.16

nable

-0.15

atura

-0.15

ultipartFile

-0.14

iquid

-0.14

reek

-0.14

iana

-0.14

.ant

-0.14

POSITIVE LOGITS

eza

0.15

erdem

0.15

 ZÃ¡p

0.15

pdf

0.15

ogany

0.14

 NhÃ¢n

0.14

omor

0.14

(defvar

0.14

tain

0.14

ATAB

0.14

Activations Density 0.018%

repeated references to the word "other."

No Comments

No Known Activations