INDEX

Explanations

terms related to medical treatments and bodily functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

áº£o

-0.15

 Gale

-0.15

hurst

-0.14

itle

-0.14

elsey

-0.14

 Depths

-0.13

pais

-0.13

 PMID

-0.13

iot

-0.13

 beyond

-0.13

POSITIVE LOGITS

 statically

0.17

/static

0.16

 inconvenient

0.15

jourd

0.15

Sed

0.15

dden

0.14

 KrÃ¡l

0.14

eydi

0.14

sed

0.14

 static

0.14

Activations Density 0.086%

terms related to medical treatments and bodily functions

No Comments

No Known Activations