INDEX

Explanations

words and phrases related to educational achievements and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

adle

-0.15

airobi

-0.15

illos

-0.15

Uhr

-0.14

 Geld

-0.14

ombo

-0.14

rote

-0.14

.sourceforge

-0.14

miss

-0.14

 sist

-0.14

POSITIVE LOGITS

 Batch

0.16

units

0.15

æīĭãģ«

0.14

æŁ³

0.14

 Ital

0.14

 Kore

0.14

 Units

0.14

 alphabet

0.14

TAM

0.13

dep

0.13

Activations Density 0.027%

words and phrases related to educational achievements and programs

No Comments

No Known Activations