INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Kong

-0.17

fer

-0.16

coni

-0.15

oto

-0.14

-functional

-0.14

 Ferry

-0.14

backward

-0.14

ometr

-0.13

bow

-0.13

pud

-0.13

POSITIVE LOGITS

/profile

0.15

UniformLocation

0.15

èµ«

0.15

çĿĽ

0.15

»

0.15

mojom

0.14

 Hlav

0.14

Įĵ

0.14

Yak

0.14

zie

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.