INDEX

Explanations

the phrase "don't" and its variants indicating a negative imperative or advice

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

erno

-0.18

ffe

-0.16

fter

-0.15

ual

-0.15

.freeze

-0.15

clide

-0.14

Å¡ak

-0.14

ually

-0.14

intl

-0.14

.pivot

-0.14

POSITIVE LOGITS

cel

0.16

indh

0.15

afari

0.14

Ð°Ð·Ð°

0.14

olith

0.14

ipers

0.14

ascus

0.14

itored

0.13

argout

0.13

chant

0.13

Activations Density 0.077%

the phrase "don't" and its variants indicating a negative imperative or advice

No Comments

No Known Activations