INDEX

Explanations

pronouns referring to individuals, particularly highlighting personal connections and relationships

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

hiba

-0.18

ingly

-0.17

tle

-0.15

emme

-0.15

biÃªn

-0.15

lect

-0.14

naire

-0.14

mey

-0.13

áºŃp

-0.13

 ALOG

-0.13

POSITIVE LOGITS

/her

0.39

/she

0.30

panic

0.20

 himself

0.18

idelberg

0.17

ewith

0.17

avier

0.17

idi

0.16

far

0.16

zelf

0.16

Activations Density 0.468%

pronouns referring to individuals, particularly highlighting personal connections and relationships

No Comments

No Known Activations