INDEX

Explanations

references to previously mentioned topics or items in the text

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

æĸĻ

-0.18

Ã¶tt

-0.17

osing

-0.17

 Pier

-0.14

ä»

-0.14

reib

-0.14

 cellFor

-0.14

orca

-0.14

 priv

-0.14

PostExecute

-0.13

POSITIVE LOGITS

odal

0.18

 aforementioned

0.17

 above

0.17

hya

0.16

Above

0.16

Ã¡le

0.15

erer

0.15

ingle

0.15

 mentioned

0.15

 yukarÄ±

0.14

Activations Density 0.182%

references to previously mentioned topics or items in the text

No Comments

No Known Activations