INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

erty

-0.15

andez

-0.15

ogan

-0.15

Sink

-0.14

oco

-0.14

-fold

-0.14

entric

-0.14

 ëĪ

-0.14

ias

-0.14

amera

-0.14

POSITIVE LOGITS

 Bars

0.17

hu

0.17

 bars

0.16

Placeholder

0.15

Mig

0.14

otron

0.14

idl

0.14

 Dunk

0.14

ossip

0.14

 shel

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.