INDEX

Explanations

phrases indicating existence or state of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

azzi

-0.17

hill

-0.16

ivr

-0.14

aux

-0.14

fir

-0.14

xon

-0.14

 wouldn

-0.14

las

-0.13

uya

-0.13

 Monroe

-0.13

POSITIVE LOGITS

prung

0.17

OSH

0.15

 Pazar

0.15

Å¡it

0.15

.twig

0.14

_PD

0.14

orias

0.14

OMPI

0.14

htub

0.13

enth

0.13

Activations Density 0.008%

phrases indicating existence or state of being

No Comments

No Known Activations