INDEX

Explanations

terms related to legal filings and petitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

/from

-0.18

oral

-0.16

Ã«l

-0.15

ake

-0.15

ana

-0.15

ran

-0.15

asser

-0.14

roe

-0.14

ya

-0.14

mega

-0.14

POSITIVE LOGITS

ì°©

0.16

iday

0.16

antry

0.16

izens

0.16

ëŁ

0.16

ician

0.16

buster

0.16

Indented

0.15

horn

0.15

:///

0.15

Activations Density 0.020%

terms related to legal filings and petitions

No Comments

No Known Activations