INDEX

Explanations

technical terms and jargon related to legal and economic contexts

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

etas

-0.18

kers

-0.17

lettes

-0.17

emas

-0.17

scripts

-0.16

links

-0.16

INFRINGEMENT

-0.16

ainers

-0.15

aments

-0.15

esktop

-0.15

POSITIVE LOGITS

MENTS

0.30

IFS

0.29

IDS

0.29

IPS

0.29

STS

0.28

ISTS

0.28

ENCES

0.28

AGES

0.28

IMS

0.28

USES

0.28

Activations Density 0.067%

technical terms and jargon related to legal and economic contexts

No Comments

No Known Activations