INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĤ§

-0.17

oring

-0.16

ade

-0.16

antu

-0.15

ugal

-0.15

PIC

-0.15

ais

-0.15

Hog

-0.14

aise

-0.14

illed

-0.14

POSITIVE LOGITS

alars

0.18

itore

0.16

raci

0.16

csi

0.16

tractor

0.16

 Quad

0.14

ecer

0.14

edn

0.14

creds

0.14

Ð¾Ð²Ð°ÑĢ

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.