INDEX

Explanations

modal verbs indicating future actions or capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Hubb

-0.16

/dc

-0.15

.qual

-0.15

atars

-0.14

 will

-0.14

Î¿Î¹

-0.14

ffd

-0.14

Ã¡ct

-0.14

://

-0.14

 Elena

-0.14

POSITIVE LOGITS

ingly

0.18

ulist

0.16

iam

0.16

IAM

0.16

fully

0.16

iams

0.16

amic

0.16

you

0.15

oom

0.15

owy

0.15

Activations Density 0.258%

modal verbs indicating future actions or capabilities

No Comments

No Known Activations