INDEX

Explanations

terms related to prediction and accuracy in scientific or technical contexts

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

.Rad

-0.18

 repmat

-0.17

mination

-0.15

à¤¸à¤Ń

-0.15

ought

-0.15

rema

-0.15

rita

-0.15

 AXIS

-0.15

-0.14

Ã©tica

-0.14

POSITIVE LOGITS

nis

0.18

 loose

0.17

 Cornell

0.16

ions

0.15

aries

0.15

nal

0.15

ql

0.15

 Hend

0.15

ãģªãģı

0.15

inceton

0.14

Activations Density 0.018%

terms related to prediction and accuracy in scientific or technical contexts

No Comments

No Known Activations