INDEX

Explanations

dates and years in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Leading

-0.16

à¹īà¸ĩ

-0.16

Operator

-0.16

alim

-0.15

Leading

-0.15

_operator

-0.15

iane

-0.15

Ä©

-0.15

 Operator

-0.14

ooth

-0.14

POSITIVE LOGITS

 Gill

0.17

0.15

eland

0.15

 Resume

0.15

 Currency

0.15

 SQLITE

0.15

 quit

0.14

-tw

0.14

aldo

0.14

Activations Density 0.049%

dates and years in various contexts

No Comments

No Known Activations