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

oftware

-0.18

ghi

-0.17

ammen

-0.17

kaar

-0.15

posables

-0.15

osate

-0.14

ispens

-0.14

ÐµÐ»ÐµÐ¼

-0.14

Äĥm

-0.14

ARB

-0.14

POSITIVE LOGITS

olo

0.17

ency

0.15

ir

0.14

enta

0.14

olas

0.14

pong

0.14

ne

0.14

ear

0.14

ster

0.14

ouns

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.