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

-0.14

amba

-0.14

¿

-0.14

amber

-0.14

ÐµÐ²Ð¸

-0.14

rog

-0.13

 addCriterion

-0.13

ichni

-0.13

veloper

-0.13

ÙĨØ´

-0.13

POSITIVE LOGITS

beck

0.15

åħ¼

0.15

ãĥ©ãĥ¼

0.14

erer

0.14

rive

0.14

intersect

0.14

_TI

0.14

ibs

0.14

esch

0.14

ombo

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.