INDEX

Explanations

symbols and formatting elements related to markup or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ramework

-0.18

à¸ª

-0.17

ockets

-0.17

ë¬¼

-0.15

-ÑĤÐ¾

-0.15

ÐµÑĢÑĪ

-0.14

↵

-0.14

Ã³rio

-0.14

eniable

-0.14

POSITIVE LOGITS

eyer

0.18

eyh

0.16

indy

0.15

udi

0.15

adele

0.14

atoi

0.14

ud

0.14

ingen

0.14

ad

0.13

IService

0.13

Activations Density 0.097%

symbols and formatting elements related to markup or code

No Comments

No Known Activations