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

innamon

-0.17

ossible

-0.15

eyn

-0.14

_exceptions

-0.14

ehir

-0.14

BOSE

-0.13

quette

-0.13

ÑĤÐ°Ð±

-0.13

ipher

-0.13

eea

-0.13

POSITIVE LOGITS

son

0.20

spath

0.16

sson

0.16

ultipart

0.16

ded

0.16

bil

0.15

ugo

0.15

inspace

0.14

gap

0.14

boo

0.14

Activations Density 0.314%

No Comments

No Known Activations