INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

imei

-0.16

Porno

-0.15

ellido

-0.15

akis

-0.14

 Sampler

-0.14

ACHINE

-0.14

Ø§Ø¨Ø¯

-0.14

Ø¨ÙĬØ¹

-0.14

ä¹ħ

-0.13

JoinColumn

-0.13

POSITIVE LOGITS

iri

0.16

ested

0.16

ursal

0.16

rels

0.15

chers

0.15

Ð¸ÐºÐ¸

0.15

holm

0.15

oire

0.14

ASTE

0.14

hardt

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.