INDEX

Explanations

phrases indicating perceptions and conclusions about situations or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

its

-0.17

ked

-0.16

 relative

-0.15

fon

-0.14

 type

-0.14

âĢ¦

-0.14

ologia

-0.14

 eventual

-0.14

enc

-0.13

POSITIVE LOGITS

 bahwa

0.18

ichel

0.15

EIF

0.15

 ráº±ng

0.15

0.14

eview

0.14

 Ð¼Ð¾Ñī

0.14

lice

0.14

ornment

0.14

unami

0.14

Activations Density 0.055%

phrases indicating perceptions and conclusions about situations or topics

No Comments

No Known Activations