INDEX

Explanations

references to specialists or specialist-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

nier

-0.18

entials

-0.17

nings

-0.15

ÑĩÐ¸Ð²

-0.15

ingham

-0.15

alom

-0.15

uese

-0.14

ration

-0.14

powered

-0.14

SearchParams

-0.14

POSITIVE LOGITS

iena

0.17

 Shir

0.17

chron

0.15

odem

0.14

mdl

0.14

rtl

0.14

Chron

0.14

à¹Ģà¸īà¸ŀà¸²à¸°

0.14

ingroup

0.14

 renamed

0.14

Activations Density 0.013%

references to specialists or specialist-related terminology

No Comments

No Known Activations