INDEX

Explanations

the preposition "in" used in 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

enga

-0.17

anka

-0.16

edo

-0.14

wich

-0.13

ovy

-0.13

InThe

-0.13

forme

-0.13

rijk

-0.13

Ã´i

-0.13

POSITIVE LOGITS

 mind

0.85

mind

0.69

 Mind

0.63

Mind

0.61

 minds

0.57

 mente

0.48

 Minds

0.43

 minded

0.35

-minded

0.27

 mindset

0.25

Activations Density 0.018%

the preposition "in" used in various contexts

No Comments

No Known Activations