INDEX

Explanations

phrases related to optimization or improving efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 trap

-0.15

 competitiveness

-0.14

von

-0.14

rogen

-0.14

aktion

-0.14

 allot

-0.14

Ãło

-0.14

ysl

-0.13

 plum

-0.13

ctors

-0.13

POSITIVE LOGITS

.CG

0.18

chemy

0.17

enso

0.17

inki

0.16

allas

0.15

icens

0.15

ç¢¼

0.14

ourt

0.14

unce

0.14

Tahoma

0.14

Activations Density 0.002%

phrases related to optimization or improving efficiency

No Comments

No Known Activations