INDEX

Explanations

phrases indicating permission or authorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

mium

-0.17

odon

-0.16

noun

-0.16

InnerText

-0.15

imary

-0.15

rame

-0.15

/exp

-0.14

.SelectedItems

-0.14

è¸

-0.14

POSITIVE LOGITS

ADM

0.16

zn

0.15

aison

0.15

ee

0.15

eh

0.15

.wik

0.14

oppins

0.14

 compar

0.14

ope

0.14

ilen

0.13

Activations Density 0.041%

phrases indicating permission or authorization

No Comments

No Known Activations