INDEX

Explanations

notable keywords and phrases indicating seriousness or significant concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

alist

-0.17

onation

-0.16

asi

-0.16

Ã¡o

-0.15

isy

-0.15

æĩ

-0.15

issance

-0.14

ataires

-0.14

onec

-0.14

à¸±à¸Ļà¸§

-0.14

POSITIVE LOGITS

Ð¾ÑĢÐ¼

0.16

antro

0.15

omb

0.14

 BÃ¶l

0.14

 Rudd

0.13

áº·n

0.13

intr

0.13

 OnTrigger

0.13

GGLE

0.13

cds

0.13

Activations Density 0.001%

notable keywords and phrases indicating seriousness or significant concepts

No Comments

No Known Activations