INDEX

Explanations

references to educational institutions and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

.sys

-0.15

inkel

-0.15

apiro

-0.14

ETO

-0.14

lio

-0.14

_lit

-0.14

Assertions

-0.14

ronym

-0.14

eto

-0.13

rompt

-0.13

POSITIVE LOGITS

amb

0.22

 Behind

0.20

 Schul

0.20

pf

0.19

 Kind

0.19

 Kinder

0.18

 Integr

0.18

Gym

0.18

Pf

0.18

Jug

0.18

Activations Density 0.016%

references to educational institutions and achievements

No Comments

No Known Activations