INDEX

Explanations

information related to approval ratings and polling data

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

rawer

-0.17

MLS

-0.15

ikt

-0.15

orna

-0.14

.setter

-0.14

achu

-0.14

MLS

-0.14

_permalink

-0.14

 damer

-0.14

ith

-0.14

POSITIVE LOGITS

 poll

0.50

 polls

0.48

poll

0.45

 polling

0.45

 Poll

0.44

Poll

0.38

.poll

0.37

 Gallup

0.36

 POLL

0.35

_poll

0.34

Activations Density 0.143%

information related to approval ratings and polling data

No Comments

No Known Activations