INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

adia

-0.18

iÃ¨re

-0.15

erd

-0.15

llib

-0.15

Ã¶l

-0.15

&C

-0.14

ling

-0.14

dy

-0.14

engl

-0.14

ought

-0.14

POSITIVE LOGITS

unan

0.16

ehr

0.16

jak

0.15

ucken

0.14

criptor

0.14

 Eins

0.14

_INLINE

0.14

Ð¾Ð¼Ñĥ

0.13

odesk

0.13

 sustain

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.