INDEX

Explanations

terms related to software components and actors involved in digital or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

eka

-0.18

ux

-0.17

eur

-0.17

ibili

-0.17

nid

-0.17

sWith

-0.16

ningen

-0.16

tain

-0.16

ek

-0.16

yor

-0.16

POSITIVE LOGITS

hip

0.37

ship

0.28

hips

0.25

-upper

0.25

/editor

0.24

/compiler

0.23

SHIP

0.23

innen

0.22

HIP

0.22

/operator

0.22

Activations Density 0.637%

terms related to software components and actors involved in digital or coding contexts

No Comments

No Known Activations