INDEX

Explanations

mentions of professional qualifications and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ikat

-0.16

plash

-0.15

etter

-0.15

hevik

-0.15

addock

-0.15

ottle

-0.14

 terk

-0.14

odka

-0.14

Kaf

-0.14

aket

-0.14

POSITIVE LOGITS

cion

0.16

 Tate

0.14

 status

0.14

 Stra

0.14

conde

0.13

 vers

0.13

rowable

0.13

 paved

0.13

dia

0.13

 Tray

0.13

Activations Density 0.034%

mentions of professional qualifications and affiliations

No Comments

No Known Activations