INDEX

Explanations

phrases related to healing processes and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ãĤ§

-0.14

adem

-0.13

éģ£

-0.13

/do

-0.13

 Priest

-0.13

egot

-0.12

yw

-0.12

OLUMN

-0.12

 Woche

-0.12

POSITIVE LOGITS

 performed

0.18

IOD

0.16

 happening

0.15

Occurred

0.15

adr

0.15

platz

0.15

hay

0.15

 conducted

0.15

Performed

0.14

à¸Ħà¸£

0.14

Activations Density 0.404%

phrases related to healing processes and their effects

No Comments

No Known Activations

phrases related to healing processes and their effects

No Comments

No Known Activations