INDEX

Explanations

comparative relationships and contrasts between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.nih

-0.18

-0.16

ÙĥØ§ÙĨ

-0.16

cano

-0.15

istar

-0.15

ulos

-0.15

.setPrototypeOf

-0.14

leri

-0.14

zew

-0.14

ktor

-0.14

POSITIVE LOGITS

 couldn

0.90

couldn

0.84

 Couldn

0.78

Couldn

0.60

 could

0.31

 Could

0.26

Could

0.26

could

0.25

 unable

0.24

 incapable

0.22

Activations Density 0.126%

comparative relationships and contrasts between entities

No Comments

No Known Activations