INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

INES

-0.16

å¹¸

-0.15

nick

-0.15

ines

-0.15

olley

-0.14

Î¹Î¬

-0.14

engo

-0.14

prox

-0.14

appa

-0.14

echa

-0.14

POSITIVE LOGITS

ardown

0.18

URY

0.17

 TMPro

0.16

alue

0.15

 egret

0.15

onian

0.14

ackle

0.14

zig

0.14

-inv

0.14

ury

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.