INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

zcze

-0.18

SACTION

-0.14

 Kids

-0.14

ActionCreators

-0.14

Kids

-0.14

yd

-0.14

 CHARSET

-0.14

jus

-0.13

ORB

-0.13

rahim

-0.13

POSITIVE LOGITS

ial

0.16

iaÅĤ

0.16

igner

0.14

esson

0.14

piar

0.14

ones

0.13

 Weiner

0.13

 tane

0.13

 bisexual

0.13

mits

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.