INDEX

Explanations

punctuation marks, particularly quotation marks and apostrophes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Carol

-0.15

riv

-0.15

 Gent

-0.15

eto

-0.15

 Ward

-0.14

 infl

-0.14

andas

-0.14

 Barb

-0.14

 perk

-0.14

 stud

-0.13

POSITIVE LOGITS

0.24

format

0.24

.format

0.20

 format

0.19

æł¼å¼ı

0.17

%(

0.17

 Format

0.17

-format

0.16

 formats

0.16

arg

0.16

Activations Density 0.004%

punctuation marks, particularly quotation marks and apostrophes

No Comments

No Known Activations