INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

GGLE

-0.15

-0.14

ie

-0.14

oft

-0.13

ÑĢÐ¾Ð³

-0.13

apot

-0.13

POSITIVE LOGITS

ipel

0.16

aty

0.15

 sona

0.15

ibel

0.15

aket

0.15

 ê²ĥëıĦ

0.15

erli

0.14

unate

0.14

Streamer

0.14

.ordinal

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.