INDEX

Explanations

references to collective events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ur

-0.17

ung

-0.16

aju

-0.14

irus

-0.14

aring

-0.14

uming

-0.14

amine

-0.14

mong

-0.14

ing

-0.14

ic

-0.14

POSITIVE LOGITS

amber

0.15

Andre

0.14

abl

0.14

 Andre

0.14

 Alec

0.13

 Hort

0.13

LinkId

0.13

utex

0.13

Ross

0.13

aleigh

0.12

Activations Density 0.027%

references to collective events or actions

No Comments

No Known Activations