INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

,,,

-0.17

chen

-0.17

kus

-0.15

eller

-0.15

 autof

-0.15

bart

-0.14

,...↵↵

-0.14

.intellij

-0.14

ollider

-0.14

å½

-0.13

POSITIVE LOGITS

styled

0.17

pec

0.15

-svg

0.14

 hala

0.14

inerary

0.14

ãĤ«ãĥĨãĤ´ãĥª

0.14

 wholesome

0.13

ecer

0.13

à¸²à¸ģà¸²à¸£

0.13

pec

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.