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

DBus

-0.16

eph

-0.16

ieten

-0.15

ort

-0.15

.DropDown

-0.14

Lei

-0.14

asje

-0.14

atz

-0.14

illus

-0.14

Ð¾Ð¶

-0.13

POSITIVE LOGITS

 âĸĪâĸĪ

0.16

eyer

0.15

 personally

0.15

_simps

0.15

egrator

0.14

ìĬ¤ì½Ķ

0.14

egrity

0.14

Blockly

0.14

_refl

0.14

 sine

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.