INDEX

Explanations

references to nationalities or ethnicities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ë§Īëĭ¤

-0.16

Äįka

-0.15

esis

-0.14

 Midi

-0.14

Ã©r

-0.13

Flo

-0.13

 Pamela

-0.13

 objective

-0.13

 Composite

-0.13

acher

-0.13

POSITIVE LOGITS

0.14

asa

0.14

æŀ

0.14

 Corner

0.14

 corner

0.14

Hoy

0.14

:async

0.13

 ÙĪØ§Ø¨

0.13

ros

0.13

lick

0.13

Activations Density 0.141%

references to nationalities or ethnicities

No Comments

No Known Activations