INDEX

Explanations

phrases and prepositions indicating inclusion and association in contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãģĲ

-0.17

chai

-0.14

çŃĭ

-0.14

ãĤĤãĤĬ

-0.14

hil

-0.13

Ð²ÐµÐ¹

-0.12

_firestore

-0.12

 Robbins

-0.12

ji

-0.12

Ã«n

-0.12

POSITIVE LOGITS

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

0.17

/of

0.15

 Insecta

0.14

 Westminster

0.13

ije

0.13

vinces

0.12

ofs

0.12

ombat

0.12

ÑĢÐ¾Ð²Ð¸Ñĩ

0.12

 VerfÃ¼gung

0.12

Activations Density 0.101%

phrases and prepositions indicating inclusion and association in contexts

No Comments

No Known Activations