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

-0.16

zcze

-0.15

-0.14

 Interracial

-0.14

bla

-0.14

tik

-0.14

-0.13

Î³Î¹

-0.13

trx

-0.13

jist

-0.13

POSITIVE LOGITS

andard

0.15

 sapi

0.15

onest

0.14

 nbytes

0.14

 Perm

0.14

ods

0.14

ondo

0.14

foc

0.14

icas

0.14

 repet

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.