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

eyer

-0.16

inch

-0.15

 Leban

-0.15

_codegen

-0.14

ãĢģãĢģ

-0.14

:CGRect

-0.14

abi

-0.14

pcf

-0.14

[js

-0.14

esian

-0.14

POSITIVE LOGITS

udson

0.15

 Vital

0.14

EVT

0.14

oto

0.14

Gas

0.13

spy

0.13

_interrupt

0.13

Pac

0.13

 Reyn

0.13

cek

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.