INDEX

Explanations

phrases related to terms and conditions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

sez

-0.17

hs

-0.16

rien

-0.16

orta

-0.16

IGHL

-0.15

dou

-0.14

pf

-0.14

alls

-0.14

ha

-0.14

ar

-0.14

POSITIVE LOGITS

exels

0.16

oins

0.16

acle

0.14

isters

0.14

gua

0.14

piler

0.14

dbus

0.14

.azure

0.13

-Encoding

0.13

 both

0.13

Activations Density 0.023%

phrases related to terms and conditions in various contexts

No Comments

No Known Activations