INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Eat

-0.17

alto

-0.17

ully

-0.15

UED

-0.15

ires

-0.14

.shiro

-0.14

qh

-0.14

elter

-0.14

POSITIVE LOGITS

INGTON

0.16

ington

0.15

Î¬Îº

0.15

tual

0.15

ddit

0.15

illa

0.14

renal

0.14

 kenn

0.14

 hÃ´m

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.