INDEX

Explanations

names of government officials and their actions

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

orny

-0.16

_INCREMENT

-0.15

ÐµÐ²Ð¸Ð´

-0.15

'gc

-0.14

veÅĻej

-0.14

avl

-0.14

lant

-0.14

acey

-0.14

ARIO

-0.14

ITH

-0.14

POSITIVE LOGITS

yleft

0.16

 relative

0.15

iser

0.14

ian

0.14

 Ware

0.14

æĳ

0.14

Wid

0.13

Relative

0.13

 Relative

0.13

lediÄŁi

0.13

Activations Density 0.015%

names of government officials and their actions

No Comments

No Known Activations