INDEX

Explanations

terms related to communication and inclusion in both medical and 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

izations

-0.18

isations

-0.16

-0.15

iken

-0.15

ieu

-0.15

angelo

-0.14

itimate

-0.14

izational

-0.14

omez

-0.14

atively

-0.14

POSITIVE LOGITS

ernet

0.17

ajo

0.16

Ð½Ð°Ð¼

0.15

ette

0.15

icides

0.15

aki

0.15

/out

0.15

ernational

0.14

ptest

0.14

ecial

0.14

Activations Density 0.077%

terms related to communication and inclusion in both medical and technical contexts

No Comments

No Known Activations