INDEX

Explanations

punctuation marks and numbers in the context of medical or clinical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ø¨Ø§Ø¯

-0.16

iddy

-0.16

LEASE

-0.15

uche

-0.15

.Mutable

-0.14

heed

-0.14

uchen

-0.14

ilogy

-0.14

dice

-0.13

 lÃ´

-0.13

POSITIVE LOGITS

 WithEvents

0.16

 clums

0.15

 side

0.15

 tram

0.15

 soma

0.14

roph

0.14

_bind

0.14

buy

0.14

azon

0.14

ãĤĬãģ¨

0.14

Activations Density 0.001%

punctuation marks and numbers in the context of medical or clinical references

No Comments

No Known Activations