INDEX

Explanations

references to legal actions and court proceedings

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

á»©ng

-0.15

umer

-0.15

 pumpkin

-0.14

esome

-0.14

ä»ĭ

-0.14

Ð»Ð¸Ñĩ

-0.14

Ã¼p

-0.14

argon

-0.14

 Barker

-0.13

ê´

-0.13

POSITIVE LOGITS

 TORT

0.18

PEnd

0.16

 Engineers

0.16

.family

0.15

ilden

0.15

 deterioration

0.15

(=)

0.15

aml

0.15

Compound

0.14

Inspectable

0.14

Activations Density 0.020%

references to legal actions and court proceedings

No Comments

No Known Activations