INDEX

Explanations

references to specific drug names and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

yal

-0.24

-0.19

yas

-0.18

ãĥ¼ãĥĦ

-0.18

XXX

-0.17

yor

-0.17

XXXX

-0.17

yi

-0.16

yan

-0.16

XX

-0.16

POSITIVE LOGITS

avier

0.26

plorer

0.25

perience

0.22

pert

0.21

tra

0.20

perimental

0.19

cellent

0.18

periment

0.18

embourg

0.18

iaomi

0.17

Activations Density 0.045%

references to specific drug names and their classifications

No Comments

No Known Activations