INDEX

Explanations

technical specifications and data formats in documentation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

idth

-0.15

orna

-0.14

inner

-0.14

reesome

-0.14

oran

-0.14

alan

-0.14

elve

-0.13

embali

-0.13

Asset

-0.13

_entropy

-0.13

POSITIVE LOGITS

 late

0.16

Ã©al

0.15

PEG

0.14

Î³ÎµÎ¹

0.14

 pseud

0.14

bi

0.14

ob

0.13

prix

0.13

xit

0.13

 purse

0.13

Activations Density 0.242%

technical specifications and data formats in documentation

No Comments

No Known Activations