INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

awa

-0.14

 Stake

-0.14

éĿĴ

-0.14

ombo

-0.14

lear

-0.14

 corp

-0.14

perse

-0.14

dm

-0.14

cyl

-0.14

kol

-0.14

POSITIVE LOGITS

 Jewish

0.18

 Jews

0.17

(((

0.16

Jew

0.16

/plugin

0.15

-Semitism

0.15

jew

0.15

atin

0.14

iales

0.14

.serialization

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.