INDEX

Explanations

references to video content and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

anh

-0.17

mann

-0.16

me

-0.15

ollo

-0.15

name

-0.15

ijd

-0.15

most

-0.15

ep

-0.15

ÑĩÐ¸Ð¼

-0.14

wart

-0.14

POSITIVE LOGITS

/audio

0.16

ERTICAL

0.15

/photo

0.15

conference

0.14

ized

0.14

imensional

0.14

IRROR

0.14

hora

0.14

zap

0.14

Activations Density 0.040%

references to video content and its various forms

No Comments

No Known Activations