INDEX

Explanations

terms related to government and organizational structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

tro

-0.15

ole

-0.15

 fore

-0.15

sta

-0.14

 PREFIX

-0.14

 dispro

-0.14

erb

-0.14

 Georg

-0.14

POSITIVE LOGITS

ì¶Ķ

0.16

ddy

0.15

agens

0.15

urch

0.14

 settlement

0.14

ynos

0.14

unctuation

0.14

á»©t

0.14

ushima

0.14

 settled

0.14

Activations Density 0.028%

terms related to government and organizational structure

No Comments

No Known Activations