INDEX

Explanations

words indicating inclusivity and the notion of choice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

é¦Ļ

-0.16

Shr

-0.15

Thunk

-0.14

 incididunt

-0.14

 podstat

-0.14

ewn

-0.14

/Gate

-0.14

 verdienen

-0.14

AndUpdate

-0.14

anou

-0.14

POSITIVE LOGITS

Tan

0.18

Tan

0.17

tan

0.16

 éĸ

0.14

da

0.14

obbies

0.14

ton

0.14

 Hopkins

0.14

.GetString

0.14

 vote

0.14

Activations Density 0.107%

words indicating inclusivity and the notion of choice

No Comments

No Known Activations