INDEX

Explanations

references to significant events in a chronological context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

sky

-0.15

uner

-0.15

ewire

-0.14

echa

-0.14

.logic

-0.14

 Whole

-0.14

aml

-0.14

 Ribbon

-0.13

ensa

-0.13

ç§

-0.13

POSITIVE LOGITS

ongyang

0.16

.gf

0.15

ItemSelected

0.15

istik

0.15

urf

0.14

bes

0.14

adoo

0.14

 Boyd

0.14

alama

0.14

alnÄ±z

0.13

Activations Density 0.046%

references to significant events in a chronological context

No Comments

No Known Activations