INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

berg

-0.16

EP

-0.16

wheel

-0.15

 Herrera

-0.15

ument

-0.14

inder

-0.14

imson

-0.14

YST

-0.14

ender

-0.14

vr

-0.14

POSITIVE LOGITS

ÅĽcie

0.17

iero

0.16

oÄŁ

0.16

icode

0.15

å¤®

0.15

ucz

0.15

Ø´ÙħØ§ÙĦÛĮ

0.14

.undefined

0.14

ERO

0.14

_Rel

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.