INDEX

Explanations

the name "Mc" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

.UTC

-0.16

apon

-0.15

ancia

-0.15

inois

-0.15

adge

-0.14

ÙĪØ§Ø¡

-0.14

recht

-0.14

¹Ħ

-0.14

Î¼Î¿

-0.14

ellite

-0.14

POSITIVE LOGITS

intosh

0.24

 Donald

0.20

LEAR

0.18

onald

0.18

nty

0.17

adden

0.17

voy

0.16

ombs

0.16

vey

0.16

Donald

0.15

Activations Density 0.023%

the name "Mc" in various contexts

No Comments

No Known Activations