INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

forcing

-0.16

ä»°

-0.15

à¥ĩà¤¶

-0.15

CTR

-0.14

ray

-0.14

ESCO

-0.14

 affairs

-0.14

lying

-0.13

minating

-0.13

esh

-0.13

POSITIVE LOGITS

ãĥ¼ãĤ¸

0.18

onn

0.18

entials

0.16

itoris

0.15

PDOException

0.15

á»«ng

0.15

hog

0.14

YPD

0.14

.inst

0.14

enstein

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.