INDEX

Explanations

expressions denoting methods or procedures for achieving goals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

fy

-0.18

achs

-0.15

ale

-0.14

esel

-0.14

yx

-0.14

aleb

-0.14

ocoa

-0.14

à¸ł

-0.14

POSITIVE LOGITS

é¡ĺ

0.17

abor

0.16

ottle

0.16

priv

0.15

relative

0.15

 Priv

0.15

 accompl

0.14

 residuals

0.14

 ÐĹÐ°Ð²

0.14

oundingBox

0.14

Activations Density 0.245%

expressions denoting methods or procedures for achieving goals

No Comments

No Known Activations