INDEX

Explanations

references to media representation of political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

/Area

-0.16

ÏĨÏħ

-0.15

rog

-0.14

 Pride

-0.14

igor

-0.14

 createAction

-0.14

allen

-0.14

rians

-0.14

 Tobias

-0.14

Transactions

-0.14

POSITIVE LOGITS

 coverage

0.22

coverage

0.18

 reporting

0.17

 outlets

0.17

-wsj

0.16

 news

0.15

/report

0.15

 Coverage

0.15

/news

0.14

eselect

0.14

Activations Density 0.100%

references to media representation of political issues

No Comments

No Known Activations