INDEX

Explanations

phrases or structures that suggest a process or method, particularly those beginning with "how to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iment

-0.19

erras

-0.15

vise

-0.14

ãģ®æĸ¹

-0.14

 Prot

-0.14

porate

-0.14

Mob

-0.14

bef

-0.14

 flexGrow

-0.14

INIT

-0.13

POSITIVE LOGITS

orthy

0.14

ewood

0.13

 Ãĸn

0.13

 Wong

0.13

igs

0.13

arkan

0.13

/autoload

0.13

Lights

0.13

ishly

0.13

Activations Density 0.012%

phrases or structures that suggest a process or method, particularly those beginning with "how to."

No Comments

No Known Activations