INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

anza

-0.19

azen

-0.14

vel

-0.14

kins

-0.14

ari

-0.14

 work

-0.13

ãĥ«ãĥķ

-0.13

 TaÅŁ

-0.13

sed

-0.13

ret

-0.13

POSITIVE LOGITS

ettle

0.17

ervo

0.16

 maduras

0.15

atura

0.15

åī¯

0.15

arges

0.14

iram

0.14

/renderer

0.14

REM

0.14

.mo

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.