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

á»ĭp

-0.15

ãģ¨ãģį

-0.15

 billig

-0.14

ãĥ³ãĤ¬

-0.14

bud

-0.13

menus

-0.13

GraphNode

-0.13

neas

-0.13

aurus

-0.13

ÙĪÙĨÙĩ

-0.13

POSITIVE LOGITS

hz

0.17

abouts

0.15

ilst

0.15

%D

0.15

_ANDROID

0.15

ulti

0.14

.undefined

0.14

akra

0.14

obot

0.14

 ÐŁÑĢÐ°

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.