INDEX

Explanations

structural elements and formatting indicators in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

aira

-0.15

 Medium

-0.14

anh

-0.14

raith

-0.14

Bol

-0.13

hd

-0.13

ucht

-0.13

ashtra

-0.13

/Library

-0.13

 Hidden

-0.13

POSITIVE LOGITS

ailles

0.18

 abbrev

0.14

ardy

0.14

ailable

0.14

^[

0.14

 *)((

0.14

 èĩ

0.14

iaux

0.14

/testify

0.13

acom

0.13

Activations Density 0.007%

structural elements and formatting indicators in text

No Comments

No Known Activations