INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 jeÅ¾

-0.16

fra

-0.14

ENTA

-0.14

Ð¾Ð±Ð°

-0.14

phan

-0.14

quete

-0.13

Ø§Ø±Ø¯

-0.13

Ð¾ÑģÑĥÐ´

-0.13

@}

-0.13

'&'

-0.13

POSITIVE LOGITS

 electric

0.17

EV

0.17

âłĢ

0.17

electric

0.17

 electr

0.17

Riv

0.17

çĶµ

0.16

Electric

0.16

acier

0.15

Bes

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.