INDEX

Explanations

corporate names and associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

itra

-0.15

 uninitialized

-0.15

ui

-0.15

ãĤ¶ãĥ¼

-0.15

lÃ¡

-0.14

ote

-0.14

cot

-0.13

IOC

-0.13

iid

-0.13

POSITIVE LOGITS

Inc

0.67

Inc

0.53

inc

0.53

inc

0.51

_inc

0.50

-inc

0.48

INC

0.47

.inc

0.43

INC

0.41

 Incorporated

0.37

Activations Density 0.075%

corporate names and associated entities

No Comments

No Known Activations