INDEX

Explanations

the name "Lawrence" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

deen

-0.17

tery

-0.16

ìłĢ

-0.16

recht

-0.15

pra

-0.15

ernity

-0.14

jian

-0.14

isol

-0.14

terra

-0.14

POSITIVE LOGITS

yer

0.20

ville

0.16

yers

0.16

 Berkeley

0.15

ãĤ¤ãĥ«

0.15

olum

0.15

unning

0.14

ptron

0.14

Erl

0.14

ade

0.14

Activations Density 0.008%

the name "Lawrence" and its variations in different contexts

No Comments

No Known Activations