INDEX

Explanations

mentions of government actions and policies

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

 earm

-0.17

èĳ£äºĭ

-0.15

apol

-0.14

 ense

-0.14

panse

-0.14

-0.13

_append

-0.13

 Spiral

-0.13

eslint

-0.13

omid

-0.13

POSITIVE LOGITS

azon

0.17

issing

0.17

 agencies

0.17

éł

0.16

mic

0.15

-cond

0.15

uctor

0.15

 funding

0.15

 subsid

0.14

igon

0.14

Activations Density 0.187%

mentions of government actions and policies

No Comments

No Known Activations