INDEX

Explanations

numerical values and statistical data related to political 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Daily

-0.17

Byl

-0.16

 piger

-0.15

 Affero

-0.15

weekly

-0.15

uis

-0.15

 daily

-0.15

daily

-0.14

olib

-0.13

Fri

-0.13

POSITIVE LOGITS

 pattern

0.18

istorical

0.17

 historical

0.17

 exception

0.17

 history

0.17

 histor

0.17

åı²

0.16

 Ð¿ÑĢÐ°Ð²Ð¸Ð»Ð¾

0.15

isel

0.15

 exceptions

0.15

Activations Density 0.046%

numerical values and statistical data related to political approval ratings

No Comments

No Known Activations