INDEX

Explanations

references to global scope or impact

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

idar

-0.16

ond

-0.15

ould

-0.14

osa

-0.14

holm

-0.14

urve

-0.14

ible

-0.14

aja

-0.14

ryptography

-0.14

POSITIVE LOGITS

/local

0.21

ITT

0.19

/global

0.19

/world

0.17

ihn

0.17

-wide

0.16

ToLocal

0.16

-reaching

0.14

/int

0.14

UnderTest

0.14

Activations Density 0.006%

references to global scope or impact

No Comments

No Known Activations