INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

inges

-0.17

udson

-0.14

ØºÙĨ

-0.14

?url

-0.14

ÑĶÐ²

-0.13

BuilderFactory

-0.13

SEX

-0.13

iloc

-0.13

 åŁ

-0.13

ATUS

-0.13

POSITIVE LOGITS

usz

0.15

 tavs

0.14

spender

0.14

 hete

0.14

 various

0.14

/**č↵

0.14

grese

0.14

è¼Ŀ

0.14

 TBranch

0.14

moy

0.13

Activations Density 0.117%

No Comments

No Known Activations