INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.MixedReality

-0.16

ghi

-0.16

IMS

-0.15

blr

-0.15

Ľå»º

-0.15

abbo

-0.14

igne

-0.14

 ping

-0.14

libft

-0.14

ÏĦÏģ

-0.14

POSITIVE LOGITS

 Hind

0.16

(#)

0.15

Dod

0.14

@[

0.14

Äĵ

0.14

uppet

0.14

lady

0.13

noon

0.13

 Fletcher

0.13

 Neville

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.