INDEX

Explanations

references to the position and actions of the U.S. President

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

NES

-0.15

nes

-0.14

»¿

-0.14

ern

-0.14

aber

-0.14

oman

-0.14

arsing

-0.14

apan

-0.14

.internet

-0.13

esser

-0.13

POSITIVE LOGITS

ships

0.18

ially

0.15

optgroup

0.14

ONGL

0.14

.Accessible

0.14

chaft

0.14

yyn

0.14

/current

0.14

«ĺ

0.14

ompiler

0.14

Activations Density 0.035%

references to the position and actions of the U.S. President

No Comments

No Known Activations