INDEX

Explanations

proper nouns, especially names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

TestFixture

-0.17

 aras

-0.16

lette

-0.15

HD

-0.15

 tails

-0.15

ifu

-0.14

ngh

-0.14

iyon

-0.14

 associ

-0.14

Nit

-0.13

POSITIVE LOGITS

Ph

0.30

ph

0.30

Ph

0.23

/ph

0.22

(ph

0.19

ippines

0.18

ph

0.18

adelphia

0.16

-ph

0.16

.ph

0.15

Activations Density 0.039%

proper nouns, especially names

No Comments

No Known Activations