INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 ðŁ

-0.17

-0.15

 emoji

-0.15

abra

-0.15

ðŁ

-0.14

 ingr

-0.14

uez

-0.14

 industries

-0.14

 ðŁĳ

-0.13

 Emoji

-0.13

POSITIVE LOGITS

 Small

0.18

 micro

0.18

Individual

0.17

.micro

0.17

 Individual

0.16

Small

0.16

idges

0.15

_micro

0.15

 network

0.15

/small

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.