INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oya

-0.19

frei

-0.16

aley

-0.16

[]{↵

-0.15

obao

-0.15

wares

-0.15

oad

-0.15

ricks

-0.14

apphire

-0.14

.setHeight

-0.14

POSITIVE LOGITS

fr

0.17

etur

0.15

igg

0.15

Bun

0.15

uais

0.14

etu

0.14

ansa

0.14

erse

0.13

psz

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.