INDEX

Explanations

references to media articles or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

adelphia

-0.16

addir

-0.15

batim

-0.15

woord

-0.15

ilk

-0.14

inalg

-0.14

FRINGEMENT

-0.14

imal

-0.14

ildo

-0.14

ESH

-0.13

POSITIVE LOGITS

0.16

inÄĽ

0.14

ToSend

0.14

sigmoid

0.14

 PureComponent

0.14

äºĳ

0.14

0.13

PIN

0.13

uly

0.13

åĩ

0.13

Activations Density 0.044%

references to media articles or publications

No Comments

No Known Activations