INDEX

Explanations

phrases related to health and medication usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

agr

-0.16

ulet

-0.15

 hormones

-0.15

olen

-0.14

ex

-0.14

agra

-0.14

igos

-0.14

ore

-0.14

sar

-0.14

POSITIVE LOGITS

áº¡n

0.19

ÑĮÑİ

0.18

azzi

0.17

IMA

0.16

rÃ¡Å¾

0.16

PerPixel

0.15

bj

0.15

stype

0.15

halt

0.14

 AÃ§

0.14

Activations Density 0.095%

phrases related to health and medication usage

No Comments

No Known Activations