INDEX

Explanations

numerical patterns or formats, particularly associated with contact information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

loff

-0.15

luk

-0.15

owi

-0.14

reira

-0.14

cribe

-0.14

prech

-0.14

lasses

-0.14

seau

-0.14

vers

-0.14

POSITIVE LOGITS

-thumbnails

0.16

 vign

0.15

UserCode

0.14

utc

0.14

 ÑĢÐ°ÑģÐº

0.14

-INF

0.13

?key

0.13

 chip

0.13

/respond

0.13

Activations Density 0.010%

numerical patterns or formats, particularly associated with contact information

No Comments

No Known Activations