INDEX

Explanations

personal pronouns and their usages within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.16

abl

-0.15

ventions

-0.15

asso

-0.14

_S

-0.14

ourse

-0.14

ansa

-0.14

SIL

-0.14

depart

-0.13

apult

-0.13

POSITIVE LOGITS

éĤª

0.15

gene

0.14

ogene

0.14

ëĮ

0.14

ÑħÐ¾Ð²

0.14

ìĨ¡

0.14

minent

0.14

ÐµÐ·

0.13

gen

0.13

estyle

0.13

Activations Density 0.013%

personal pronouns and their usages within the text

No Comments

No Known Activations