INDEX

Explanations

phrases relating to social norms and values

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

OLT

-0.17

ops

-0.15

egra

-0.15

rows

-0.15

APH

-0.15

asti

-0.15

.rows

-0.14

enda

-0.14

orr

-0.14

 forks

-0.14

POSITIVE LOGITS

ochen

0.17

yÃ¼k

0.15

iggs

0.15

adle

0.15

ç¼

0.14

 Stuff

0.14

etc

0.14

 quot

0.14

nas

0.14

 Rails

0.14

Activations Density 0.318%

phrases relating to social norms and values

No Comments

No Known Activations