INDEX

Explanations

titles and positions of authority within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ì§

-0.16

acic

-0.16

ACES

-0.15

entine

-0.15

adoo

-0.15

adin

-0.15

atology

-0.14

ingo

-0.14

ãĤ«ãĥ¼

-0.14

POSITIVE LOGITS

ords

0.16

uder

0.16

plits

0.15

eks

0.14

ãĥĨãĥ«

0.14

hum

0.14

 Ryder

0.14

anson

0.14

wargs

0.14

ennen

0.14

Activations Density 0.044%

titles and positions of authority within organizations

No Comments

No Known Activations