INDEX

Explanations

references to influential figures or groundbreaking contributors in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Colleg

-0.15

åı£

-0.15

ake

-0.15

ten

-0.15

teg

-0.14

ark

-0.14

 underlying

-0.14

 Bernstein

-0.14

ask

-0.14

 priorit

-0.14

POSITIVE LOGITS

0.18

LEGRO

0.17

onz

0.15

CodeAt

0.15

 Robbins

0.15

.RequestMethod

0.15

hma

0.15

DIRECTORY

0.14

PointF

0.14

uars

0.14

Activations Density 0.004%

references to influential figures or groundbreaking contributors in various fields

No Comments

No Known Activations