INDEX

Explanations

comparative phrases indicating a preference or judgment of better than

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

ainers

-0.15

@$_

-0.15

ÐºÐ¾Ð´

-0.14

turnstile

-0.14

illery

-0.14

 Wald

-0.13

 Defensive

-0.13

rÅ¾

-0.13

utow

-0.13

POSITIVE LOGITS

å½¦

0.15

Hag

0.15

wl

0.14

pie

0.14

onse

0.14

illard

0.13

ipa

0.13

 Mint

0.13

elas

0.13

brtc

0.13

Activations Density 0.026%

comparative phrases indicating a preference or judgment of better than

No Comments

No Known Activations