INDEX

Explanations

references to introversion and extraversion in social 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

gro

-0.16

laps

-0.16

stile

-0.15

cab

-0.15

åĺ

-0.15

Ta

-0.15

Ta

-0.14

 nale

-0.14

æīĭ

-0.14

ITE

-0.14

POSITIVE LOGITS

ãĥ³ãĥĦ

0.17

pline

0.15

ÐµÐ½Ð·

0.15

ãĤ§

0.15

ÏĦÏĮ

0.14

wers

0.14

orris

0.14

ÐµÐ½Ñģ

0.14

anske

0.14

verted

0.14

Activations Density 0.029%

references to introversion and extraversion in social contexts

No Comments

No Known Activations