INDEX

Explanations

phrases that indicate a lack of accountability or follow-through

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

no

-0.16

 addCriterion

-0.16

æĹł

-0.14

eldorf

-0.14

ufen

-0.14

icone

-0.14

pong

-0.14

ATUS

-0.13

uku

-0.13

çĦ¡

-0.13

POSITIVE LOGITS

 little

0.53

 next

0.48

little

0.48

 precious

0.47

next

0.41

 Next

0.38

Next

0.35

(next

0.34

_next

0.34

 very

0.34

Activations Density 0.231%

phrases that indicate a lack of accountability or follow-through

No Comments

No Known Activations