INDEX

Explanations

terms related to governance and political themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÑĦÐµÐº

-0.18

_MISC

-0.16

olla

-0.16

uen

-0.16

-notes

-0.15

appa

-0.15

nota

-0.15

Ð°Ð½ÐºÐ°

-0.15

emd

-0.15

asset

-0.15

POSITIVE LOGITS

Ð½Ð¸ÑĨÐµ

0.22

ke

0.20

 ÑĦÐ¾ÑĢÐ¼Ðµ

0.20

ake

0.20

kke

0.19

iture

0.19

cce

0.18

bove

0.18

ÐºÐµ

0.18

iske

0.18

Activations Density 0.007%

terms related to governance and political themes

No Comments

No Known Activations