INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÑģÐ¾ÑĢ

-0.16

 commission

-0.16

ikan

-0.16

iphy

-0.15

itant

-0.15

axies

-0.14

hiba

-0.14

 Serif

-0.14

fos

-0.14

aba

-0.14

POSITIVE LOGITS

SSIP

0.15

essian

0.15

ç·

0.14

pj

0.14

pace

0.14

ÏģÏİÎ½

0.14

beg

0.13

.space

0.13

beg

0.13

dock

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.