INDEX

Explanations

words related to attributes and classifications of substances or entities, particularly in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Merc

-0.15

elf

-0.15

ows

-0.15

oleon

-0.15

 reverse

-0.15

 bows

-0.14

iven

-0.14

ess

-0.14

inema

-0.14

çĳ

-0.14

POSITIVE LOGITS

EMPLARY

0.17

aginator

0.17

nice

0.16

Łèĥ½

0.16

ogui

0.15

uchar

0.14

/co

0.14

atism

0.14

alion

0.14

nob

0.14

Activations Density 0.057%

words related to attributes and classifications of substances or entities, particularly in scientific contexts

No Comments

No Known Activations