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

ourke

-0.16

inger

-0.16

coma

-0.16

ocz

-0.15

shan

-0.15

orman

-0.15

igkeit

-0.15

zano

-0.15

 patch

-0.14

shaw

-0.14

POSITIVE LOGITS

ocol

0.16

odu

0.15

lingen

0.15

ifest

0.14

IMS

0.14

0.13

 Charter

0.13

efined

0.13

MethodImpl

0.13

Activations Density 0.021%

No Comments

No Known Activations