INDEX

Explanations

references to specific locations and entities, particularly in a business or news context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

arry

-0.15

icked

-0.15

leh

-0.14

 Crawford

-0.14

asad

-0.14

 sklad

-0.14

olidays

-0.14

é¾

-0.14

Iso

-0.14

olute

-0.14

POSITIVE LOGITS

inous

0.16

ç¾½

0.15

oca

0.15

tie

0.14

.asp

0.14

 gÃ¶tÃ¼r

0.14

å¥Ĺ

0.14

inou

0.14

uze

0.13

ebek

0.13

Activations Density 0.779%

references to specific locations and entities, particularly in a business or news context

No Comments

No Known Activations