INDEX

Explanations

references to significant tennis tournaments and championships

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

itia

-0.15

 compositions

-0.14

 htonl

-0.14

dy

-0.14

ibs

-0.14

-0.13

lak

-0.13

ÙĪØ«

-0.13

errat

-0.13

_ib

-0.13

POSITIVE LOGITS

anic

0.17

aroo

0.15

lectron

0.15

aN

0.15

entai

0.15

EIF

0.14

anst

0.14

 ëıĦ

0.14

anto

0.14

 Straw

0.14

Activations Density 0.018%

references to significant tennis tournaments and championships

No Comments

No Known Activations