INDEX

Explanations

words associated with energy policies and their impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

èĻİ

-0.16

ORY

-0.15

eri

-0.15

 Stout

-0.15

edla

-0.14

ãģ¿

-0.14

æ¹¾

-0.14

orical

-0.14

.Null

-0.14

uchs

-0.14

POSITIVE LOGITS

amburg

0.17

 Acres

0.16

blas

0.15

ä»°

0.15

lick

0.14

éĬ·

0.14

ubi

0.14

 Winn

0.14

illas

0.14

 bure

0.14

Activations Density 0.441%

words associated with energy policies and their impacts

No Comments

No Known Activations