INDEX

Explanations

names of places and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

genome

-0.15

ÎºÏĦÎ·

-0.14

scala

-0.14

 Jinping

-0.13

opal

-0.13

ãģıãĤĵ

-0.13

ÙıÙĩ

-0.13

æ¦ľ

-0.13

Bang

-0.13

-cigaret

-0.12

POSITIVE LOGITS

 Witch

0.34

 Goddess

0.30

 witch

0.29

 witches

0.28

 Magick

0.28

 Druid

0.27

 Craft

0.27

witch

0.26

cov

0.25

 goddess

0.25

Activations Density 0.023%

names of places and events

No Comments

No Known Activations