INDEX

Explanations

phrases indicating choices or options involving multiple parties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ø¬Ùħ

-0.14

 Singap

-0.14

 æ¤

-0.14

Ø§ØŃÙĦ

-0.13

deÅŁ

-0.13

orer

-0.13

]|[

-0.13

ater

-0.13

linkplain

-0.13

braco

-0.12

POSITIVE LOGITS

 again

0.17

again

0.17

 Again

0.15

nown

0.14

Again

0.14

ingleton

0.14

 itself

0.14

ëŀĻ

0.14

neider

0.14

 permanently

0.13

Activations Density 0.009%

phrases indicating choices or options involving multiple parties

No Comments

No Known Activations