INDEX

Explanations

phrases or terms related to detailed descriptions of processes or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ruta

-0.15

ias

-0.15

 darm

-0.15

/ws

-0.15

inx

-0.15

erson

-0.15

ereo

-0.15

acÃŃ

-0.15

_lens

-0.14

ÐµÐºÑĤÐ¾ÑĢ

-0.14

POSITIVE LOGITS

by

0.29

 ØªÙĪØ³Ø·

0.23

 oleh

0.23

 bá»Łi

0.23

 przez

0.16

toFloat

0.16

_by

0.16

entic

0.15

istory

0.15

onsense

0.15

Activations Density 1.362%

phrases or terms related to detailed descriptions of processes or conditions

No Comments

No Known Activations