INDEX

Explanations

references to incidents involving rescue operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ë¯

-0.15

Reminder

-0.15

ISA

-0.15

 paginate

-0.14

.snapshot

-0.14

ãĤĩ

-0.14

_DIP

-0.14

 Micha

-0.14

arkin

-0.14

IDGET

-0.14

POSITIVE LOGITS

0.16

lep

0.16

 taken

0.16

 cooperative

0.15

 eventual

0.15

 sorting

0.15

 coherent

0.15

vey

0.15

 inventory

0.15

Activations Density 0.146%

references to incidents involving rescue operations

No Comments

No Known Activations