INDEX

Explanations

keywords related to health and religious 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

thalm

-0.15

[list

-0.15

ãĥ«ãĥĪ

-0.14

ucu

-0.14

ucher

-0.14

arti

-0.13

izer

-0.13

ari

-0.13

POSITIVE LOGITS

ehr

0.17

intl

0.16

earn

0.15

adr

0.15

hed

0.15

ë¦¬ë¡ľ

0.14

 massaggi

0.14

ondo

0.14

Î¼Î¿Î½

0.14

Yaz

0.14

Activations Density 0.001%

keywords related to health and religious contexts

No Comments

No Known Activations