INDEX

Explanations

questions related to identity and role recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

issant

-0.15

PerPixel

-0.15

addtogroup

-0.15

Ú©Ùĩ

-0.15

ä¹Ī

-0.14

aja

-0.14

anson

-0.14

ehir

-0.14

setVisibility

-0.14

inqu

-0.14

POSITIVE LOGITS

/w

0.18

uras

0.17

 your

0.15

auga

0.15

/is

0.15

Roy

0.15

uki

0.14

worthy

0.14

opsis

0.14

enos

0.14

Activations Density 0.048%

questions related to identity and role recognition

No Comments

No Known Activations