INDEX

Explanations

references to medical conditions and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

éł¼

-0.15

 svensk

-0.15

emet

-0.14

dog

-0.13

ÂŃi

-0.13

stk

-0.13

esta

-0.13

bad

-0.13

Ã³st

-0.13

ermen

-0.13

POSITIVE LOGITS

0.16

bsp

0.16

ongsTo

0.15

ioxide

0.15

 inout

0.14

rÃ¥

0.14

 Dhabi

0.14

setQuery

0.14

edition

0.14

beit

0.14

Activations Density 0.019%

references to medical conditions and related terms

No Comments

No Known Activations