INDEX

Explanations

phrases and references related to legal, regulatory, or statutory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

mes

-0.18

mes

-0.16

gress

-0.15

enheim

-0.15

FIELDS

-0.15

angan

-0.15

 privilege

-0.15

eÄį

-0.15

utorial

-0.14

æį

-0.14

POSITIVE LOGITS

 brand

0.16

ucha

0.15

 Diet

0.14

 Show

0.14

tent

0.14

brand

0.14

uda

0.14

enda

0.14

lock

0.14

ubre

0.14

Activations Density 0.021%

phrases and references related to legal, regulatory, or statutory contexts

No Comments

No Known Activations