INDEX

Explanations

references to specific time periods, including years, months, and significant events

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

edo

-0.16

queeze

-0.15

Gro

-0.15

.MEDIA

-0.15

Gro

-0.14

assis

-0.14

amel

-0.14

Ð½Ð°Ð¼

-0.14

 Team

-0.14

 Sawyer

-0.14

POSITIVE LOGITS

RPC

0.15

AndUpdate

0.14

xFFF

0.14

inja

0.14

facet

0.14

 Aires

0.14

Ø§Ø²ÛĮ

0.14

ãĥªãĥ¼

0.14

oi

0.14

Khi

0.14

Activations Density 1.075%

references to specific time periods, including years, months, and significant events

No Comments

No Known Activations