INDEX

Explanations

textual features or symbols that indicate specific entities or key elements in a document

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

 learnt

-0.15

HQ

-0.15

 centre

-0.15

ajo

-0.15

 programmes

-0.15

 centres

-0.15

 behaviour

-0.14

 Firstly

-0.14

 fibre

-0.14

centre

-0.14

POSITIVE LOGITS

 colon

0.22

colon

0.19

 colonial

0.19

mast

0.18

 advertisers

0.17

 subscribers

0.17

 inserted

0.17

 insert

0.17

 Colon

0.17

Colon

0.17

Activations Density 0.002%

textual features or symbols that indicate specific entities or key elements in a document

No Comments

No Known Activations