INDEX

Explanations

references to numbers and their significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ing

-0.16

Ð²Ðµ

-0.15

rop

-0.15

war

-0.15

ings

-0.15

ITTE

-0.14

ViewHolder

-0.14

seed

-0.14

idelberg

-0.14

er

-0.14

POSITIVE LOGITS

UpDown

0.20

eral

0.20

osity

0.18

ismatic

0.18

ical

0.17

ICAL

0.17

Ã©rique

0.17

 Bris

0.17

rical

0.15

ERO

0.15

Activations Density 0.015%

references to numbers and their significance in various contexts

No Comments

No Known Activations