INDEX

Explanations

proper nouns related to names, roles, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

‘

-0.25

–

-0.19

‘

-0.18

Behaviour

-0.17

âĢĲ

-0.17

 âĢĲ

-0.17

 fibre

-0.17

 jewellery

-0.16

 recognised

-0.16

’

-0.15

POSITIVE LOGITS

 Azure

0.22

"--

0.19

Azure

0.18

 apparently

0.18

"[

0.18

 purported

0.16

 reportedly

0.16

zure

0.16

 Microsoft

0.16

LOPT

0.15

Activations Density 0.004%

proper nouns related to names, roles, and organizations

No Comments

No Known Activations