INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

rep

-0.16

jmp

-0.16

ripple

-0.15

çı¾

-0.15

earer

-0.14

äººäºº

-0.14

orum

-0.13

etooth

-0.13

POSITIVE LOGITS

vÄĽ

0.17

ukan

0.16

inka

0.16

 suce

0.16

.crm

0.15

/stdc

0.15

erne

0.15

ace

0.15

angs

0.14

ierung

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.