INDEX

Explanations

references to political events and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

agna

-0.17

.sax

-0.15

_RB

-0.14

adow

-0.14

eton

-0.13

obar

-0.13

hed

-0.13

orro

-0.13

isses

-0.13

akra

-0.13

POSITIVE LOGITS

ä»£

0.15

avern

0.15

 mandates

0.15

 distant

0.14

 natural

0.14

 mandate

0.14

/renderer

0.14

xic

0.14

Î²Î¹

0.13

incip

0.13

Activations Density 0.034%

references to political events and figures

No Comments

No Known Activations