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

nds

-0.17

ubo

-0.16

ieu

-0.15

Å¡ku

-0.15

ofi

-0.15

 ----------------------------------------------------------------------------↵

-0.15

ght

-0.14

inee

-0.14

 prow

-0.14

 Carlson

-0.14

POSITIVE LOGITS

uli

0.15

Moder

0.15

hi

0.15

fos

0.15

ev

0.14

 decom

0.14

occasion

0.14

&&&&

0.14

ura

0.14

hi

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.