INDEX

Explanations

phrases indicating intention or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ucer

-0.19

Ø³ØªØ§ÙĨ

-0.15

isin

-0.15

hd

-0.15

hop

-0.13

lyph

-0.13

arin

-0.13

æľ«

-0.13

omon

-0.13

ustry

-0.13

POSITIVE LOGITS

Pros

0.15

orp

0.15

(;;

0.15

ÙİÙī

0.15

REET

0.15

owo

0.15

ĶåĽŀ

0.14

uro

0.14

ioned

0.14

oin

0.14

Activations Density 0.011%

phrases indicating intention or purpose

No Comments

No Known Activations