INDEX

Explanations

references to personality types, particularly introversion and extroversion

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

ldr

-0.16

 Lage

-0.15

rum

-0.15

adge

-0.15

adoo

-0.14

qa

-0.14

quette

-0.14

kuk

-0.14

ucken

-0.14

acas

-0.14

POSITIVE LOGITS

0.15

 Mattis

0.15

ennon

0.15

anya

0.14

 makeup

0.14

.imag

0.14

à¥īà¤²

0.14

 personality

0.14

Wed

0.14

Activations Density 0.016%

references to personality types, particularly introversion and extroversion

No Comments

No Known Activations