INDEX

Explanations

items or components in a structured listing format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

pt

-0.17

ars

-0.14

vana

-0.14

 Keith

-0.14

 Femme

-0.14

umeric

-0.14

ÏģÎµ

-0.14

CCD

-0.13

¬

-0.13

eing

-0.13

POSITIVE LOGITS

izo

0.18

iju

0.17

ihan

0.16

EDITOR

0.15

.Experimental

0.15

0.14

.updateDynamic

0.14

oux

0.14

adas

0.14

interopRequire

0.14

Activations Density 0.138%

items or components in a structured listing format

No Comments

No Known Activations