INDEX

Explanations

proper nouns, particularly names of places and people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

efon

-0.15

orra

-0.15

LIKELY

-0.14

alace

-0.14

uong

-0.14

tega

-0.14

ulate

-0.14

-0.13

arring

-0.13

å¯¾

-0.13

POSITIVE LOGITS

ogh

0.15

 freopen

0.14

und

0.14

ãĤ¦

0.14

ossip

0.13

ount

0.13

anky

0.13

 Matte

0.13

 Äĳáº·t

0.13

unt

0.13

Activations Density 0.343%

proper nouns, particularly names of places and people

No Comments

No Known Activations