INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-pill

-0.15

inder

-0.15

abis

-0.14

_due

-0.14

atta

-0.14

enko

-0.14

 ours

-0.13

 thá»ĳng

-0.13

_STATIC

-0.13

nda

-0.13

POSITIVE LOGITS

 prox

0.16

 Actually

0.16

Actually

0.15

prox

0.15

 actually

0.15

 whereas

0.14

 sort

0.14

elo

0.14

 product

0.14

ëł´

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.