INDEX

Explanations

proper nouns and specific references related to names, titles, or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ANGO

-0.14

eneric

-0.14

uhan

-0.14

 Ð¿Ð»Ð¾ÑĤ

-0.14

ql

-0.14

vn

-0.14

ixon

-0.14

bul

-0.13

nici

-0.13

à¸²à¸«

-0.13

POSITIVE LOGITS

è¡¡

0.15

inen

0.14

Ð¸Ð½ÐºÑĥ

0.14

åħ¥ãĤĬ

0.14

ìĤ°

0.14

elig

0.13

encer

0.13

isper

0.13

 Reflect

0.13

ÙĪÙĬØ±

0.13

Activations Density 0.870%

proper nouns and specific references related to names, titles, or organizations

No Comments

No Known Activations