INDEX

Explanations

references to academic authors or citations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Malloc

-0.17

iche

-0.16

nze

-0.15

illy

-0.15

å¿ľ

-0.15

-0.14

anz

-0.14

Lam

-0.14

lad

-0.14

automation

-0.14

POSITIVE LOGITS

al

0.40

.al

0.20

ao

0.19

 others

0.17

ai

0.17

seq

0.17

al

0.16

iological

0.16

others

0.15

 Hodg

0.15

Activations Density 0.010%

references to academic authors or citations

No Comments

No Known Activations