INDEX

Explanations

references to legislative processes and political figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

.navigator

-0.16

kou

-0.15

 Tits

-0.15

iverz

-0.14

eyse

-0.14

_OPERATION

-0.14

meden

-0.14

igenous

-0.14

shed

-0.14

hei

-0.14

POSITIVE LOGITS

orna

0.16

alace

0.16

ifa

0.15

plr

0.15

éĪ

0.15

leta

0.14

poly

0.14

 addCriterion

0.14

 Major

0.14

 Choice

0.13

Activations Density 0.033%

references to legislative processes and political figures

No Comments

No Known Activations