INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

uilder

-0.16

uth

-0.16

Ã¼Ã§Ã¼k

-0.15

ãģĤãģĴ

-0.15

inst

-0.14

artin

-0.14

edo

-0.14

spar

-0.14

ofs

-0.14

èµ·

-0.14

POSITIVE LOGITS

 sorts

0.17

ÎµÎ»

0.16

 Sorting

0.16

Sort

0.15

_sort

0.15

 putas

0.14

/frontend

0.14

Î½Î±Î½

0.14

wizard

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.