INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

vester

-0.15

chied

-0.15

ediator

-0.15

spm

-0.14

USTOM

-0.14

quia

-0.14

Ownership

-0.14

asje

-0.14

Ð°Ð¶

-0.13

Ral

-0.13

POSITIVE LOGITS

0.15

 vids

0.15

-Origin

0.13

å®Ĺ

0.13

 observable

0.13

 celebr

0.13

 shall

0.12

err

0.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.