INDEX

Explanations

text indicating the original source or publication of an article

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

etch

-0.16

lk

-0.15

ocha

-0.15

 Tato

-0.14

amus

-0.14

istrovstvÃŃ

-0.14

à¤¸à¤Ń

-0.14

ami

-0.14

æľºåħ³

-0.14

ÑģÑĤÐ²Ð¾ÑĢ

-0.13

POSITIVE LOGITS

æİ¨

0.16

oga

0.16

CHED

0.15

gql

0.14

à¤¾à¤¯à¤¨

0.14

 Outlet

0.14

ÙĬØ«

0.13

 hire

0.13

incl

0.13

%%

0.13

Activations Density 0.005%

text indicating the original source or publication of an article

No Comments

No Known Activations