INDEX

Explanations

references to professional credentials and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ihan

-0.18

rÃ¡

-0.17

ks

-0.16

semb

-0.15

spath

-0.15

Ð»Ð¾Ð¹

-0.14

jÃŃ

-0.14

pii

-0.14

rade

-0.13

tal

-0.13

POSITIVE LOGITS

 Platt

0.14

illac

0.14

 Ã¢

0.14

apg

0.14

 temper

0.14

linger

0.13

 Ãĥ

0.13

DDR

0.13

 drift

0.13

ADR

0.13

Activations Density 0.009%

references to professional credentials and qualifications

No Comments

No Known Activations