INDEX

Explanations

words and phrases related to personality traits, specifically 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ide

-0.15

 Pest

-0.14

aldo

-0.14

 Platt

-0.14

leigh

-0.14

ringe

-0.14

eÄį

-0.14

otton

-0.14

eton

-0.14

 Monroe

-0.14

POSITIVE LOGITS

unm

0.17

imar

0.16

version

0.15

verts

0.15

ãĥ¼ãĥŃ

0.15

 estate

0.14

prung

0.14

ool

0.14

Gel

0.14

super

0.14

Activations Density 0.027%

words and phrases related to personality traits, specifically introversion and extroversion

No Comments

No Known Activations