INDEX

Explanations

concepts related to bias and the impact of various factors on research outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

æ®¿

-0.16

ICAST

-0.15

hei

-0.15

à¸ķà¸Ļ

-0.14

Mismatch

-0.14

?action

-0.14

annis

-0.14

ieme

-0.14

imson

-0.13

assa

-0.13

POSITIVE LOGITS

à¸´à¹Ĥ

0.17

andler

0.16

 Forward

0.15

BJ

0.15

dain

0.14

apture

0.14

 Capture

0.14

Cancellation

0.14

Bij

0.14

ducible

0.14

Activations Density 0.081%

concepts related to bias and the impact of various factors on research outcomes

No Comments

No Known Activations