INDEX

Explanations

occurrences of the word "register" and related terms, indicating a focus on registration actions or prompts

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

 Flat

-0.15

 flat

-0.15

reta

-0.15

 Quote

-0.15

()(

-0.15

<quote

-0.14

_flat

-0.14

.flat

-0.14

-flat

-0.14

ansa

-0.14

POSITIVE LOGITS

mig

0.15

amburg

0.15

ombo

0.15

sterreich

0.15

ires

0.15

à¸¥à¸°

0.15

feld

0.14

unkt

0.14

iris

0.14

ByKey

0.14

Activations Density 0.028%

occurrences of the word "register" and related terms, indicating a focus on registration actions or prompts

No Comments

No Known Activations