INDEX

Explanations

occurrences of the word "article" related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Haskell

-0.17

APH

-0.16

Äįky

-0.15

ment

-0.15

afen

-0.14

vat

-0.14

íĳľ

-0.14

ardown

-0.14

dismiss

-0.14

ë¶

-0.14

POSITIVE LOGITS

0.17

 declarations

0.16

owl

0.16

 æŁ

0.15

uco

0.15

 Spread

0.15

 æ¹

0.15

oron

0.15

Activations Density 0.026%

occurrences of the word "article" related to various contexts

No Comments

No Known Activations