INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ocha

-0.18

 Loop

-0.15

inz

-0.15

 Shapiro

-0.15

 verr

-0.14

phe

-0.14

ipher

-0.14

unken

-0.14

vette

-0.14

 inst

-0.14

POSITIVE LOGITS

]={↵

0.17

ingroup

0.15

getDisplay

0.15

ilerine

0.14

/preferences

0.14

,eg

0.14

 visite

0.14

.hr

0.14

utr

0.14

quo

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.