INDEX

Explanations

specific pronouns and references to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

acas

-0.18

aces

-0.16

th

-0.16

phin

-0.15

ugo

-0.15

à¸£à¸ĵ

-0.14

 COMPUT

-0.14

mach

-0.14

Trust

-0.14

weis

-0.14

POSITIVE LOGITS

koli

0.17

kili

0.16

_traits

0.15

ocrat

0.15

RLF

0.15

_intr

0.15

0.14

ÐµÐ»ÑĮÐ·Ñı

0.14

coln

0.14

éļĨ

0.14

Activations Density 0.250%

specific pronouns and references to individuals

No Comments

No Known Activations