INDEX

Explanations

terminology related to legal contexts and procedural language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

nap

-0.19

ÑĢÐ°Ð±

-0.16

rap

-0.15

utto

-0.15

wil

-0.15

ohl

-0.14

ders

-0.14

amu

-0.14

 kles

-0.14

ados

-0.14

POSITIVE LOGITS

icket

0.19

 Reserve

0.17

 conc

0.15

 reserve

0.15

 Cunning

0.14

 Reserved

0.14

Pag

0.14

exampleModal

0.14

ntl

0.14

ãĤĥ

0.14

Activations Density 0.007%

terminology related to legal contexts and procedural language

No Comments

No Known Activations

terminology related to legal contexts and procedural language

No Comments

No Known Activations