INDEX

Explanations

phrases indicating personal agency and the role of individuals in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 sometimes

-0.18

sometimes

-0.17

amp

-0.16

 wherever

-0.15

 rather

-0.15

 much

-0.15

 Sometimes

-0.15

may

-0.15

 cope

-0.15

rus

-0.14

POSITIVE LOGITS

 rÃ©uss

0.18

adel

0.16

 fail

0.16

æĹıèĩªæ²»

0.16

$MESS

0.16

 succeeds

0.15

NamedQuery

0.15

fail

0.15

 Truly

0.15

 truly

0.15

Activations Density 0.147%

phrases indicating personal agency and the role of individuals in various contexts

No Comments

No Known Activations