INDEX

Explanations

terms related to health conditions and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

mont

-0.16

idon

-0.16

unas

-0.16

oku

-0.15

pedia

-0.15

requete

-0.14

 Ð½Ð°ÑģÑĤÑĥÐ¿

-0.14

istrov

-0.14

itas

-0.14

afone

-0.14

POSITIVE LOGITS

 prim

0.15

 points

0.14

 Nixon

0.14

sw

0.14

iets

0.14

é³´

0.14

Points

0.13

wil

0.13

 Hughes

0.13

 navigator

0.13

Activations Density 0.221%

terms related to health conditions and their effects

No Comments

No Known Activations