INDEX

Explanations

technical terms related to data handling and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

á»ĭa

-0.12

uvw

-0.12

imde

-0.11

 Eudicots

-0.11

Î³Î¿Ïį

-0.10

.SystemColors

-0.10

Ø´Ø¯

-0.10

ÙĨØ¯ÛĮ

-0.10

áº¯

-0.10

âĶģâĶ

-0.10

POSITIVE LOGITS

 Trans

1.12

-trans

1.06

trans

1.06

 trans

1.03

Trans

1.02

 TRANS

1.00

_trans

0.94

 transf

0.94

 TRAN

0.92

TRANS

0.92

Activations Density 0.649%

technical terms related to data handling and medical conditions

No Comments

No Known Activations