INDEX

Explanations

mentions of accessible online resources and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

pars

-0.15

º

-0.15

-0.14

cab

-0.14

cab

-0.14

gn

-0.14

cta

-0.14

AKE

-0.13

Plugin

-0.13

Tre

-0.13

POSITIVE LOGITS

wargs

0.17

 INCLUDED

0.16

aho

0.16

linger

0.16

 Sanford

0.16

arti

0.16

 Included

0.15

 Pant

0.15

unks

0.14

yll

0.14

Activations Density 0.378%

mentions of accessible online resources and services

No Comments

No Known Activations