INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÎµÎ¯Î¿

-0.16

olik

-0.16

-0.15

elo

-0.14

AFX

-0.14

ÙĬÙĦØ©

-0.14

 Decomp

-0.14

perature

-0.13

[^

-0.13

POSITIVE LOGITS

chl

0.15

aec

0.15

ocument

0.15

 explanations

0.14

ptron

0.14

 presently

0.14

 Needed

0.13

 protected

0.13

utes

0.13

ged

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.