INDEX

Explanations

personal narratives involving decision-making and experiences

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

Seen

-0.16

 witnessed

-0.15

åıĳçİ°

-0.15

Liked

-0.15

 omas

-0.15

 Hindered

-0.15

seen

-0.14

heard

-0.14

 received

-0.14

 encountered

-0.14

POSITIVE LOGITS

 decided

0.23

 decide

0.23

 decides

0.20

 resolved

0.20

 headed

0.19

 resolve

0.19

dec

0.19

DEC

0.19

 devised

0.19

 resort

0.19

Activations Density 0.311%

personal narratives involving decision-making and experiences

No Comments

No Known Activations