INDEX

Explanations

references to news agencies and media reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ø§ØªÙĩ

-0.16

anian

-0.15

 Recording

-0.15

 Recorder

-0.15

 recorder

-0.15

onian

-0.15

ãĤīãģĦ

-0.15

sons

-0.14

 Magnum

-0.14

hea

-0.14

POSITIVE LOGITS

imary

0.17

ynet

0.16

aira

0.15

áº«n

0.14

 procur

0.14

 sunshine

0.14

duit

0.14

Uri

0.14

alah

0.14

 disposition

0.14

Activations Density 0.137%

references to news agencies and media reporting

No Comments

No Known Activations