INDEX

Explanations

references to organizations, committees, and political groups, particularly those associated with funding and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

udic

-0.16

ffe

-0.14

lij

-0.14

 suitability

-0.14

rij

-0.14

Pok

-0.14

edom

-0.13

deps

-0.13

 firms

-0.13

 Kash

-0.13

POSITIVE LOGITS

 operating

0.29

 existence

0.28

 exists

0.26

 operated

0.25

 exist

0.24

 Exist

0.24

 existed

0.24

 operate

0.23

 ìļ´ìĺģ

0.23

run

0.23

Activations Density 0.620%

references to organizations, committees, and political groups, particularly those associated with funding and governance

No Comments

No Known Activations