INDEX

Explanations

expressions related to inevitability and outcomes

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

Ø²Ø§Ø±

-0.18

EMPL

-0.17

ajan

-0.16

dal

-0.14

oba

-0.14

 vÅ¯bec

-0.14

Î»Î¯

-0.14

 itemprop

-0.14

_mgmt

-0.14

Ø§Ø¬Ø±

-0.14

POSITIVE LOGITS

 eventually

0.41

 Eventually

0.36

 eventual

0.35

Eventually

0.34

 sooner

0.28

 ultimately

0.23

 soon

0.21

event

0.21

oner

0.21

 EVENT

0.18

Activations Density 0.198%

expressions related to inevitability and outcomes

No Comments

No Known Activations