INDEX

Explanations

phrases indicating regulatory or legal references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

agger

-0.14

 tempt

-0.13

 èĭ±

-0.13

 Stokes

-0.13

atab

-0.13

 Maxim

-0.13

PEC

-0.13

icode

-0.13

 suspend

-0.13

yx

-0.13

POSITIVE LOGITS

nict

0.18

Ð¾Ð´ÐµÐ¹ÑģÑĤÐ²

0.16

adle

0.15

Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

0.14

uridad

0.14

 Gratuit

0.14

merce

0.14

 Pence

0.14

 Crowley

0.14

erece

0.14

Activations Density 0.264%

phrases indicating regulatory or legal references

No Comments

No Known Activations