INDEX

Explanations

references to judicial rulings and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.17

-0.16

-0.14

rox

-0.14

ullen

-0.14

iglia

-0.14

 Martinez

-0.14

istro

-0.14

ville

-0.13

aaaa

-0.13

POSITIVE LOGITS

aper

0.17

ofday

0.16

hots

0.16

antor

0.15

apest

0.15

entr

0.15

 Camel

0.15

enthal

0.15

jsc

0.15

ç´

0.14

Activations Density 0.014%

references to judicial rulings and decisions

No Comments

No Known Activations