INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eÄį

-0.15

 Injury

-0.14

izioni

-0.14

 indiv

-0.14

 Window

-0.14

buz

-0.14

utches

-0.14

imeline

-0.14

ARSER

-0.14

 informal

-0.13

POSITIVE LOGITS

CLR

0.16

lor

0.16

egl

0.15

Ú

0.15

0.14

ur

0.13

èŀį

0.13

SED

0.13

Activations Density 0.599%

No Comments

No Known Activations