INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 offending

-0.14

ãĤ²

-0.13

Sk

-0.13

nore

-0.13

 Thursday

-0.13

milliseconds

-0.13

 models

-0.13

tab

-0.12

 Sens

-0.12

 offenders

-0.12

POSITIVE LOGITS

Ð²Ð¸Ð´

0.15

gren

0.14

anning

0.14

oter

0.14

egie

0.14

indrome

0.14

antt

0.14

 tolik

0.13

 Mellon

0.13

Ð¾ÑģÑĤÑĥÐ¿

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.