INDEX

Explanations

punctuation and common auxiliary verbs in the text

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

ampa

-0.15

_simps

-0.15

ÂŃi

-0.14

 ÚĨØ´Ùħ

-0.14

loid

-0.14

stadt

-0.14

 Pearce

-0.13

uler

-0.13

 ÙĦÙĥØ±Ø©

-0.13

POSITIVE LOGITS

 Cove

0.15

 circles

0.15

uncture

0.14

isseur

0.14

aten

0.14

Ã¼f

0.14

itant

0.14

avia

0.13

Fallback

0.13

 Î²Î¬

0.13

Activations Density 0.513%

punctuation and common auxiliary verbs in the text

No Comments

No Known Activations