INDEX

Explanations

comparative phrases emphasizing preference

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

ÑģÑıÐ³

-0.14

olest

-0.14

selling

-0.14

æ´ª

-0.14

CRM

-0.14

etimes

-0.13

sold

-0.13

closure

-0.13

uem

-0.13

arrass

-0.13

POSITIVE LOGITS

ãĥªãĥ¼ãĤº

0.14

 Provid

0.14

 excit

0.14

ern

0.14

zer

0.14

ÙĬ

0.14

vide

0.14

ifs

0.14

 CONSEQUENTIAL

0.13

Activations Density 0.008%

comparative phrases emphasizing preference

No Comments

No Known Activations