INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

row

-0.14

ellen

-0.14

stp

-0.14

ogle

-0.13

 Bootstrap

-0.13

chat

-0.13

avad

-0.13

icide

-0.13

POSITIVE LOGITS

Mam

0.16

ÑĦÑĦ

0.15

åĢ

0.14

',)↵

0.13

 foil

0.13

mam

0.13

ichni

0.13

å®ļ

0.13

AppState

0.13

Ð°Ð½Ð¸ÑĨ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.