INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

rous

-0.15

iyan

-0.15

odesk

-0.14

Äįky

-0.14

Ã¶n

-0.14

fdf

-0.14

mere

-0.14

dash

-0.14

esc

-0.14

 Ð°Ð½Ð³Ð»

-0.14

POSITIVE LOGITS

DownList

0.17

 older

0.16

_DIGEST

0.16

oldem

0.15

ategorized

0.15

OLDER

0.15

VERTISE

0.15

.Percent

0.15

æĿĤ

0.14

ibling

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.