INDEX

Explanations

references to financial times and related indices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iali

-0.17

ile

-0.15

 Canter

-0.15

qing

-0.14

 dialect

-0.14

Ø§ØªÛĮ

-0.14

-0.13

 dams

-0.13

ilet

-0.13

atts

-0.13

POSITIVE LOGITS

.addAction

0.18

cac

0.16

eced

0.14

aylor

0.14

ÅĻed

0.14

 ÙĪØ§ÙĨ

0.14

alc

0.14

adera

0.13

entimes

0.13

edish

0.13

Activations Density 0.011%

references to financial times and related indices

No Comments

No Known Activations