INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ily

-0.16

lobber

-0.16

ges

-0.16

uster

-0.15

 hack

-0.15

ows

-0.14

hem

-0.14

hack

-0.14

enia

-0.14

estructor

-0.14

POSITIVE LOGITS

iqu

0.16

-Line

0.14

 Verde

0.14

ticker

0.13

 nÃło

0.13

_managed

0.13

Bau

0.13

bout

0.13

Activations Density 0.006%

No Comments

No Known Activations