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

¯

-0.17

illas

-0.15

 signed

-0.15

ollar

-0.15

ault

-0.15

 proof

-0.14

illin

-0.14

eryl

-0.14

illon

-0.14

_PROTO

-0.14

POSITIVE LOGITS

essa

0.17

uyá»ħn

0.16

_LCD

0.15

grim

0.14

antz

0.13

æŁ±

0.13

Î¼ÎµÏģÎ¿

0.13

´Ī

0.13

åĿª

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.