INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

roj

-0.16

verity

-0.15

 Stanton

-0.15

umd

-0.14

Äįet

-0.14

greater

-0.14

Inset

-0.14

(Constant

-0.14

.Invariant

-0.13

POSITIVE LOGITS

 manual

0.22

 semi

0.20

ellig

0.20

 conflicts

0.18

 conflict

0.18

 migration

0.17

 resp

0.17

 Semi

0.17

semi

0.17

 Conflict

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.