INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

prend

-0.14

ichten

-0.14

ocket

-0.14

osph

-0.14

okud

-0.14

eree

-0.13

ilk

-0.13

vak

-0.13

branch

-0.13

POSITIVE LOGITS

inia

0.15

ruba

0.15

Ã¡no

0.15

izo

0.15

iglia

0.14

oppins

0.14

bgcolor

0.14

Zone

0.14

Mid

0.14

ate

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.