INDEX

Explanations

patterns related to date and time entries

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

cname

-0.16

inia

-0.15

ä¸ĢåĮº

-0.15

:↵↵↵↵↵↵

-0.15

-0.14

egen

-0.14

egan

-0.14

olk

-0.14

oup

-0.13

Generated

-0.13

POSITIVE LOGITS

 imperson

0.15

tor

0.15

quis

0.15

utter

0.15

 Svens

0.14

_:*

0.14

bris

0.14

Snapshot

0.14

 Energ

0.14

Gee

0.14

Activations Density 0.418%

patterns related to date and time entries

No Comments

No Known Activations