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

 [...]↵↵

-0.15

allen

-0.15

imers

-0.14

Ð³Ñĥ

-0.14

ÅĻej

-0.14

Ð°Ð»Ñĥ

-0.14

noc

-0.13

ãģĭãģĳ

-0.13

azzi

-0.13

ÙĨØ§ÙĨ

-0.13

POSITIVE LOGITS

 :↵

0.18

 Town

0.17

 ours

0.17

 :↵↵

0.17

0.16

į

0.16

 town

0.16

 Brent

0.16

0.15

ourn

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.