INDEX

Explanations

references to privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.17

Han

-0.14

.dsl

-0.14

 Dort

-0.14

Ñİ

-0.14

avigate

-0.14

ingham

-0.14

onavir

-0.13

Bookmark

-0.13

NotFoundError

-0.13

POSITIVE LOGITS

mpar

0.17

mong

0.16

eum

0.14

ampp

0.14

ucas

0.14

ContextHolder

0.14

æĥħ

0.13

 compass

0.13

à¤Ŀ

0.13

 surrounding

0.13

Activations Density 0.025%

references to privacy policies

No Comments

No Known Activations