INDEX

Explanations

references to parks and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Å¾e

-0.17

ÅŁk

-0.17

TY

-0.17

arkin

-0.16

agle

-0.16

Ð³Ð»

-0.16

Ð²Ð°Ð½Ð½Ñı

-0.16

dÃ¼r

-0.16

Å¾en

-0.16

gth

-0.15

POSITIVE LOGITS

inson

0.28

land

0.24

itecture

0.22

side

0.21

lands

0.21

edly

0.21

itect

0.19

platz

0.19

our

0.19

ways

0.18

Activations Density 0.028%

references to parks and their features

No Comments

No Known Activations