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

 Decoration

-0.14

aina

-0.14

 Dillon

-0.14

ophil

-0.13

eno

-0.13

_dash

-0.13

olumn

-0.13

 èĳ

-0.13

 olsun

-0.13

up

-0.13

POSITIVE LOGITS

Borders

0.15

avra

0.14

innie

0.14

raf

0.14

ë©

0.14

 desar

0.14

utr

0.14

 prof

0.14

eur

0.13

 UTIL

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.