INDEX

Explanations

occurrences of the word "de" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ullan

-0.15

iminal

-0.15

prar

-0.15

ÑĤÑĮ

-0.15

rende

-0.14

Ð¾ÑģÑĮ

-0.14

 tvÃ¡

-0.14

stime

-0.14

_CLR

-0.14

à¸£à¸¡

-0.14

POSITIVE LOGITS

lux

0.14

Ĳ

0.14

ASIC

0.14

itos

0.14

Ð½Ð¾ÑģÐ¸

0.14

anel

0.14

SIG

0.13

 Bellev

0.13

ENCH

0.13

defer

0.13

Activations Density 0.004%

occurrences of the word "de" and its variations

No Comments

No Known Activations