INDEX

Explanations

terms and phrases related to year-round activities and seasonal features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

jed

-0.16

eba

-0.15

lient

-0.15

onya

-0.15

oday

-0.15

Ð²Ðµ

-0.15

hey

-0.14

esty

-0.14

erde

-0.14

vertiser

-0.14

POSITIVE LOGITS

-season

0.18

ths

0.18

 season

0.17

0.15

season

0.15

 Bark

0.14

/on

0.14

ØªØ¯

0.14

anchor

0.14

/by

0.14

Activations Density 0.014%

terms and phrases related to year-round activities and seasonal features

No Comments

No Known Activations