INDEX

Explanations

phrases indicating success or achievement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ongyang

-0.16

hiba

-0.16

à¤¾à¤ªà¤¨

-0.16

urovision

-0.15

Ð¾ÑĨÐ¸

-0.15

riÃ¨re

-0.15

fte

-0.15

.normalized

-0.14

 prostitut

-0.14

quat

-0.14

POSITIVE LOGITS

eras

0.17

 surviv

0.17

 Surv

0.16

Surv

0.16

0.15

tre

0.15

 Beetle

0.15

ayaran

0.14

 surviving

0.14

zar

0.14

Activations Density 0.104%

phrases indicating success or achievement

No Comments

No Known Activations