INDEX

Explanations

instances of the word "Originally" indicating the origin or background information about a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ystack

-0.16

ito

-0.16

ading

-0.14

Î²Î¬

-0.14

pong

-0.14

Ade

-0.14

ernels

-0.14

.Tick

-0.13

.atom

-0.13

pany

-0.13

POSITIVE LOGITS

ister

0.14

zej

0.14

emoc

0.13

keiten

0.13

 meis

0.13

oda

0.13

é¼»

0.13

 êµŃë¯¼

0.13

 Resolver

0.13

fol

0.13

Activations Density 0.002%

instances of the word "Originally" indicating the origin or background information about a subject

No Comments

No Known Activations