INDEX

Explanations

references to federal legal proceedings and charges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 poison

-0.17

esch

-0.17

es

-0.16

ÑĸÐ»ÑĮ

-0.15

news

-0.15

 Pole

-0.14

Ã¤l

-0.14

akis

-0.14

POSITIVE LOGITS

Ð»Ð°Ð¼

0.18

ambi

0.16

artment

0.15

ertas

0.15

Ð¶Ðµ

0.15

CHANT

0.15

ãĥ³ãĤº

0.14

uter

0.14

ternet

0.14

ICO

0.14

Activations Density 0.013%

references to federal legal proceedings and charges

No Comments

No Known Activations