INDEX

Explanations

keywords and phrases that indicate important locations, solutions, and relationships within 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

olt

-0.15

ella

-0.15

Ð¾ÑĩÐºÑĥ

-0.14

ouis

-0.14

abr

-0.14

ORIA

-0.14

åħ¶ä¸Ń

-0.13

alic

-0.13

allet

-0.13

POSITIVE LOGITS

romatic

0.15

ÙĬØ©

0.14

iest

0.14

ufe

0.14

Ø²ÙĪ

0.14

_taxonomy

0.13

ipt

0.13

neys

0.13

HQ

0.13

Activations Density 0.177%

keywords and phrases that indicate important locations, solutions, and relationships within the text

No Comments

No Known Activations