INDEX

Explanations

political metrics and approval ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ibri

-0.17

_representation

-0.16

ietet

-0.15

Ã©ny

-0.15

UCCESS

-0.15

roz

-0.14

Ã³j

-0.14

UIL

-0.14

Qui

-0.14

ena

-0.14

POSITIVE LOGITS

 approval

0.28

 Approval

0.24

 approvals

0.23

 approve

0.23

approval

0.23

approve

0.21

Approval

0.20

 ratings

0.20

 Ratings

0.19

 rating

0.19

Activations Density 0.033%

political metrics and approval ratings

No Comments

No Known Activations