INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

FTWARE

-0.17

ftware

-0.16

TEGER

-0.15

UTERS

-0.15

uben

-0.14

AdapterFactory

-0.14

-centered

-0.14

CACHE

-0.14

Apart

-0.14

.metro

-0.13

POSITIVE LOGITS

icha

0.15

ÙĦØ§Øª

0.14

elter

0.14

_MIC

0.14

 everybody

0.14

 Everybody

0.14

 invokes

0.13

 adversaries

0.13

 previews

0.13

AllWindows

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.