INDEX

Explanations

references to postage stamps and postal services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ches

-0.17

-0.16

vi

-0.16

dash

-0.15

ty

-0.15

abis

-0.15

pool

-0.15

esc

-0.15

POSITIVE LOGITS

antium

0.20

ocaly

0.18

 ëĦ¤ìĿ´íĬ¸

0.17

 servisi

0.17

ëĦ

0.17

kah

0.17

 servis

0.16

rchive

0.16

icana

0.16

ardless

0.15

Activations Density 0.157%

references to postage stamps and postal services

No Comments

No Known Activations