INDEX

Explanations

arguments and discussions related to education and government policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rieve

-0.19

áº¿p

-0.14

isp

-0.14

uai

-0.14

reek

-0.14

uto

-0.14

leine

-0.14

 velk

-0.13

duk

-0.13

acer

-0.13

POSITIVE LOGITS

 should

0.21

 Should

0.16

.argument

0.16

è®º

0.15

 argument

0.15

è«ĸ

0.15

Argument

0.15

 shouldn

0.15

vs

0.15

 controvers

0.15

Activations Density 0.265%

arguments and discussions related to education and government policies

No Comments

No Known Activations