INDEX

Explanations

references to legal sentences and criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ardy

-0.17

-0.15

createView

-0.14

alue

-0.14

 sworn

-0.14

kea

-0.14

ÑĢÑĥÐ´

-0.14

 setattr

-0.14

POSITIVE LOGITS

 sentence

0.50

 convictions

0.46

 conviction

0.46

 sentences

0.45

Sentence

0.42

 Sentence

0.41

 Conv

0.41

 sentenced

0.40

conv

0.40

sentence

0.39

Activations Density 0.107%

references to legal sentences and criminal activities

No Comments

No Known Activations