INDEX

Explanations

references to fairness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

naire

-0.17

egasus

-0.16

esc

-0.16

ectomy

-0.15

tingham

-0.15

chef

-0.14

ÏĢÎ¿

-0.14

ential

-0.14

editor

-0.14

chin

-0.14

POSITIVE LOGITS

grounds

0.18

asan

0.17

ground

0.17

aisal

0.16

aban

0.16

weather

0.16

ably

0.16

mount

0.15

yt

0.15

ness

0.15

Activations Density 0.025%

references to fairness in various contexts

No Comments

No Known Activations