INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 mult

-0.15

 later

-0.15

 wives

-0.15

 marginal

-0.14

 proto

-0.14

son

-0.14

 spouses

-0.14

Ã¼m

-0.14

ui

-0.14

 https

-0.14

POSITIVE LOGITS

 Recovery

0.19

/english

0.17

 recovery

0.16

ictionary

0.15

 Recover

0.15

´ĳ

0.15

fkk

0.14

_recovery

0.14

aravel

0.14

 advoc

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.