INDEX

Explanations

conditional phrases and phrases indicating changes or uncertainties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

avery

-0.15

iggs

-0.14

aceous

-0.14

 Kurulu

-0.14

warz

-0.14

urma

-0.13

iele

-0.13

APPER

-0.13

POSITIVE LOGITS

gon

0.15

urr

0.14

jad

0.13

onders

0.13

etch

0.13

er

0.12

lap

0.12

aight

0.12

rary

0.12

pref

0.12

Activations Density 0.193%

conditional phrases and phrases indicating changes or uncertainties

No Comments

No Known Activations