INDEX

Explanations

references to regulatory agencies and government entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

sembly

-0.15

kate

-0.14

 creep

-0.14

BuilderInterface

-0.14

Ã»

-0.14

Plate

-0.14

apat

-0.14

.setColumns

-0.14

gul

-0.13

POSITIVE LOGITS

-approved

0.18

à¸Ńà¸Ļ

0.17

.gov

0.17

-required

0.17

allows

0.16

-san

0.16

 allows

0.15

 allowing

0.15

alia

0.14

_APPRO

0.14

Activations Density 0.305%

references to regulatory agencies and government entities

No Comments

No Known Activations