INDEX

Explanations

references to various types of facilities and their functions, particularly in research and commercial settings

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

jan

-0.18

 Bren

-0.15

 Epic

-0.14

[s

-0.14

 Carnegie

-0.14

ere

-0.14

stu

-0.13

POSITIVE LOGITS

abcdefghijkl

0.19

posable

0.15

Unload

0.15

abcdefghijklmnop

0.15

=-=-

0.14

ductor

0.14

@student

0.14

sumer

0.14

pper

0.14

EMY

0.14

Activations Density 0.166%

references to various types of facilities and their functions, particularly in research and commercial settings

No Comments

No Known Activations