INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

anax

-0.15

ouro

-0.15

uncios

-0.15

usercontent

-0.15

anst

-0.14

quip

-0.14

ursal

-0.14

ptrdiff

-0.14

illon

-0.14

 Deploy

-0.14

POSITIVE LOGITS

 developmental

0.16

lor

0.15

ãģĵãĤĵ

0.15

 stocks

0.15

åĶ¯

0.14

 commits

0.14

 Luft

0.14

rÅ¯

0.14

deen

0.14

à¸±à¸ģà¸Ķ

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.