INDEX

Explanations

references to academic or governmental organizations and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Mos

-0.15

moth

-0.14

Vic

-0.14

.AddTransient

-0.14

RowAt

-0.14

Informe

-0.13

Âģ

-0.13

 antic

-0.13

æ£ļ

-0.13

POSITIVE LOGITS

opi

0.15

ometr

0.15

ounters

0.15

º

0.15

lav

0.15

bum

0.15

ãĤĩ

0.14

.mdl

0.14

à¸«à¸Ļ

0.14

 dames

0.14

Activations Density 0.124%

references to academic or governmental organizations and their activities

No Comments

No Known Activations