INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

rove

-0.17

Î¸Î¼

-0.17

antis

-0.16

aminer

-0.15

ctl

-0.14

itto

-0.14

tram

-0.14

nad

-0.14

æĪĴ

-0.14

roke

-0.13

POSITIVE LOGITS

-scalable

0.15

celik

0.14

vez

0.14

Ø§Ø²Ùħ

0.14

PTS

0.14

cura

0.13

oman

0.13

Ð°ÑĤÐ¾ÑĢÐ°

0.13

Interpreter

0.13

ÙħÙĪÙĦ

0.13

Activations Density 0.025%

No Comments

No Known Activations