INDEX

Explanations

expressions that suggest attempts or recommendations for action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ronic

-0.15

elsey

-0.15

 confl

-0.14

udur

-0.14

adil

-0.14

í

-0.14

uther

-0.14

plib

-0.14

 roman

-0.14

entr

-0.14

POSITIVE LOGITS

0.17

 Incoming

0.14

ÙĪÙĦÙĪ

0.14

.asp

0.14

0.13

-NLS

0.13

 okol

0.13

avoid

0.13

iform

0.13

Activations Density 0.047%

expressions that suggest attempts or recommendations for action

No Comments

No Known Activations