INDEX

Explanations

phrases indicating familiarity or awareness of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

mina

-0.16

adolu

-0.15

oplan

-0.15

idle

-0.15

itas

-0.14

Ð·Ð²

-0.14

ddit

-0.14

 Cout

-0.14

.tc

-0.14

 ÑħÐ²

-0.13

POSITIVE LOGITS

ington

0.15

ÐĴÑĸÐ´

0.15

ie

0.15

INGTON

0.14

IFO

0.14

hi

0.14

.Ac

0.14

edores

0.14

reck

0.14

 kind

0.14

Activations Density 0.021%

phrases indicating familiarity or awareness of information

No Comments

No Known Activations