INDEX

Explanations

terminology related to cookies and user personalization on websites

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Ð¾Ð¶ÐµÑĤ

-0.15

ÙģØ§ÙĦ

-0.15

ogan

-0.15

ucken

-0.15

ë¶Ī

-0.14

æķ

-0.14

 APPLE

-0.14

 Lowest

-0.14

ell

-0.14

athy

-0.14

POSITIVE LOGITS

ozo

0.15

omas

0.14

olithic

0.14

rai

0.14

ifique

0.14

 Silence

0.13

 ofrece

0.13

hest

0.13

 Dump

0.13

Î´Î¬

0.13

Activations Density 0.020%

terminology related to cookies and user personalization on websites

No Comments

No Known Activations