INDEX

Explanations

references to regulations, disclaimers, and relationships in promotional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

orph

-0.17

obia

-0.17

alytics

-0.16

gie

-0.15

Ð¾Ð´Ð°ÑĢ

-0.15

jay

-0.14

Won

-0.14

.Interop

-0.14

 Codes

-0.14

Pdf

-0.14

POSITIVE LOGITS

nor

0.33

nor

0.24

NOR

0.20

Nor

0.19

Nor

0.19

umbs

0.19

any

0.18

 endorsement

0.18

 endorse

0.17

ä»»ä½ķ

0.17

Activations Density 0.035%

references to regulations, disclaimers, and relationships in promotional contexts

No Comments

No Known Activations