INDEX

Explanations

references to product lines and launches in technology and consumer goods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

agna

-0.16

istrovstvÃŃ

-0.15

lopen

-0.14

iem

-0.14

ÅĻÃŃd

-0.14

,readonly

-0.12

 nexus

-0.12

ropy

-0.12

alem

-0.12

Ð¾Ð»Ð¾Ñģ

-0.12

POSITIVE LOGITS

 range

0.72

 ranges

0.59

range

0.59

 Range

0.54

-range

0.52

Range

0.50

 line

0.49

 RANGE

0.47

_range

0.47

ranges

0.46

Activations Density 0.257%

references to product lines and launches in technology and consumer goods

No Comments

No Known Activations