INDEX

Explanations

punctuation marks and their context in structured data or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

For

-0.23

It

-0.23

 There

-0.21

 With

-0.20

If

-0.20

 After

-0.20

 Since

-0.19

 Although

-0.19

 While

-0.19

 When

-0.19

POSITIVE LOGITS

sig

0.14

.MixedReality

0.14

âĢİ

0.14

(Unknown

0.14

ros

0.14

Unnamed

0.14

soever

0.14

erno

0.13

ennen

0.13

HEME

0.13

Activations Density 0.188%

punctuation marks and their context in structured data or lists

No Comments

No Known Activations