INDEX

Explanations

emphatic expressions and variations of the term "man" used in conversational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

uzzer

-0.16

ullo

-0.16

 dilig

-0.16

ahren

-0.15

ç©¶

-0.15

apos

-0.15

ãĥ¼ãĥ¬

-0.15

ozem

-0.15

acies

-0.15

 Affero

-0.14

POSITIVE LOGITS

STER

0.16

LEGRO

0.15

kin

0.14

kin

0.14

Ã¼rk

0.14

Fol

0.14

OSP

0.14

avo

0.13

aleb

0.13

Activations Density 0.092%

emphatic expressions and variations of the term "man" used in conversational contexts

No Comments

No Known Activations