INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

leo

-0.15

 Dillon

-0.14

hoff

-0.14

rew

-0.14

Stub

-0.13

_fc

-0.13

spd

-0.13

]()

-0.13

references

-0.13

leanup

-0.13

POSITIVE LOGITS

ignon

0.15

olland

0.15

dense

0.14

VILLE

0.14

ute

0.14

idal

0.14

.Dense

0.14

itez

0.13

annya

0.13

à¸Ļà¸²à¸Ķ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.