INDEX

Explanations

references to Vice President Kamala Harris and her political role

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

incinn

-0.16

_ASCII

-0.16

ampa

-0.15

ewe

-0.15

ummies

-0.15

pent

-0.14

ocha

-0.14

yonel

-0.14

Hra

-0.14

POSITIVE LOGITS

olini

0.15

iz

0.14

ndon

0.13

egan

0.13

/world

0.13

Liz

0.13

Hof

0.13

.createComponent

0.13

ahn

0.13

Pil

0.13

Activations Density 0.019%

references to Vice President Kamala Harris and her political role

No Comments

No Known Activations