INDEX

Explanations

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

:^

-0.16

unta

-0.15

mey

-0.15

ror

-0.15

etsk

-0.15

vise

-0.15

Ð¾Ð»Ð¸ÑĤ

-0.15

aub

-0.15

abox

-0.14

eted

-0.14

POSITIVE LOGITS

0.15

ostel

0.14

bruar

0.13

XD

0.13

recio

0.13

 stead

0.13

HV

0.13

,:,

0.13

 Jacobs

0.13

Activations Density 0.027%

proper nouns, particularly names and titles

No Comments

No Known Activations