INDEX

Explanations

references to authors or scholars, particularly those with initials and a surname format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

illes

-0.17

agg

-0.16

odyn

-0.15

iform

-0.15

born

-0.15

ainless

-0.15

AGR

-0.15

ynam

-0.14

AGMA

-0.14

engin

-0.14

POSITIVE LOGITS

pei

0.17

oust

0.16

Ńå·ŀ

0.16

ãĥ¼ãĤ¿

0.15

elin

0.14

.connector

0.14

pez

0.14

ixture

0.14

 Bacon

0.14

 Barton

0.14

Activations Density 0.072%

references to authors or scholars, particularly those with initials and a surname format

No Comments

No Known Activations