INDEX

Explanations

expressions of personal experience and introspection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

riv

-0.17

riv

-0.16

vard

-0.16

 reporter

-0.15

 enhance

-0.15

 enhancement

-0.15

 darn

-0.14

 Andersen

-0.14

 enhanced

-0.14

ê°ĢìļĶ

-0.14

POSITIVE LOGITS

 fucks

0.19

 fuck

0.18

 Fuck

0.18

 fucked

0.18

 FUCK

0.16

 haha

0.16

 shit

0.16

ourn

0.15

Ã¨o

0.15

 shitty

0.15

Activations Density 0.260%

expressions of personal experience and introspection

No Comments

No Known Activations