INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ø§ÙĬØ¯

-0.16

LOBAL

-0.15

bole

-0.13

jid

-0.13

 Ø£ÙĬØ¶

-0.13

-themed

-0.13

bie

-0.13

laus

-0.13

iah

-0.13

pector

-0.13

POSITIVE LOGITS

åĳĨ

0.15

enario

0.15

oft

0.15

 topo

0.14

RED

0.14

 splitted

0.14

 alike

0.13

axon

0.13

osu

0.13

iment

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.