INDEX

Explanations

references to time and duration related to spans, periods, or years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.synthetic

-0.14

egend

-0.14

orney

-0.14

kili

-0.14

á»ĵng

-0.14

Î²Îµ

-0.14

linkplain

-0.14

TS

-0.14

jes

-0.14

/Math

-0.14

POSITIVE LOGITS

Ä±k

0.16

Culture

0.16

UpDown

0.15

Dyn

0.15

 span

0.15

ATAR

0.15

ÌĤ

0.14

 culture

0.14

Activations Density 0.012%

references to time and duration related to spans, periods, or years

No Comments

No Known Activations