INDEX

Explanations

phrases indicating quantity or measurement related to "out of" contexts

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

ãģĹãĤĩ

-0.17

ÙİÙĬ

-0.15

frey

-0.15

ContextHolder

-0.15

.='

-0.15

ements

-0.14

quette

-0.14

erna

-0.14

inger

-0.14

æĻ´

-0.14

POSITIVE LOGITS

ters

0.23

wards

0.16

/out

0.15

 bounds

0.15

ensive

0.15

done

0.15

ensively

0.15

atatype

0.14

 reach

0.14

 khá»ıi

0.14

Activations Density 0.057%

phrases indicating quantity or measurement related to "out of" contexts

No Comments

No Known Activations