INDEX

Explanations

punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.19

-0.17

aje

-0.16

ombat

-0.15

andro

-0.15

INS

-0.14

atto

-0.14

ÐµÐ»ÑĮÐ·Ñı

-0.14

 PVOID

-0.14

erm

-0.14

POSITIVE LOGITS

ndern

0.16

 Vert

0.15

vip

0.15

Nug

0.14

Ú¯Ø§Ùĩ

0.14

ivia

0.14

GRAM

0.14

 ÄĳÃłi

0.14

Vert

0.13

vari

0.13

Activations Density 0.000%

punctuation marks

No Comments

No Known Activations