INDEX

Explanations

words and phrases indicating success or achievement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

alla

-0.17

ezi

-0.16

Ø³Ø±

-0.16

âĢĮØ§ÙĨ

-0.15

cil

-0.15

alle

-0.15

ibar

-0.14

apor

-0.14

bine

-0.14

ssel

-0.14

POSITIVE LOGITS

 completion

0.20

lest

0.17

completion

0.17

 defended

0.17

 outcome

0.16

ness

0.16

 Completion

0.16

 completed

0.15

Ð·ÑĮ

0.15

 transition

0.15

Activations Density 0.082%

words and phrases indicating success or achievement

No Comments

No Known Activations