INDEX

Explanations

names and references associated with individuals or characters

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

ecom

-0.18

IQ

-0.17

entlich

-0.15

ocket

-0.15

hod

-0.15

ec

-0.15

 è©

-0.15

nette

-0.15

han

-0.14

.sendStatus

-0.14

POSITIVE LOGITS

gerald

0.21

ual

0.17

tier

0.17

ually

0.17

ubishi

0.16

ausal

0.16

patrick

0.15

uality

0.15

ÐµÑĢÐ°ÑĤÑĥÑĢÐ°

0.15

ty

0.15

Activations Density 0.035%

names and references associated with individuals or characters

No Comments

No Known Activations