INDEX

Explanations

references to informational content and relevant topics across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

jo

-0.15

oc

-0.14

iddle

-0.14

ysa

-0.13

pets

-0.13

Lun

-0.13

å³¶

-0.13

 compile

-0.12

itle

-0.12

POSITIVE LOGITS

argas

0.20

è°±

0.17

reff

0.16

opoulos

0.15

 nackte

0.15

Ð²Ð°Ð½Ð°

0.14

hazi

0.14

EventArgs

0.14

uyla

0.14

ainless

0.14

Activations Density 0.048%

references to informational content and relevant topics across various contexts

No Comments

No Known Activations