INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

atch

-0.15

ott

-0.15

otts

-0.15

enzie

-0.14

VID

-0.14

iert

-0.14

/light

-0.14

iyan

-0.14

amy

-0.14

POSITIVE LOGITS

 Perr

0.15

-grade

0.15

'na

0.14

 Penal

0.14

/business

0.14

ecs

0.14

yg

0.13

 grade

0.13

 Prest

0.13

iska

0.13

Activations Density 0.143%

No Comments

No Known Activations