INDEX

Explanations

instances of the verb "to be" and its various forms in relation to professions or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

izon

-0.15

ens

-0.15

ajar

-0.15

anders

-0.14

NameValuePair

-0.14

Ã¸

-0.14

enders

-0.14

ogram

-0.13

-CS

-0.13

achi

-0.13

POSITIVE LOGITS

utschen

0.15

ï¸

0.15

phalt

0.15

ÏĦÏĥ

0.15

IRCLE

0.14

kne

0.14

vents

0.13

 âĺĨ

0.13

 Ø·Ø¨ÙĬ

0.13

ÑĨÐ¾

0.13

Activations Density 0.044%

instances of the verb "to be" and its various forms in relation to professions or roles

No Comments

No Known Activations