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

iro

-0.17

asic

-0.16

adas

-0.14

uess

-0.14

 clue

-0.14

shint

-0.14

 Fauc

-0.14

ÎºÎŃ

-0.14

Í

-0.14

erness

-0.14

POSITIVE LOGITS

ãĤ¯ãĥĪ

0.15

sei

0.15

 å¹³æĸ¹

0.14

offsetof

0.14

_UNITS

0.14

_blend

0.14

.synthetic

0.14

ichi

0.14

 Seah

0.14

 ******************************************************************************↵

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.