INDEX

Explanations

mentions of software, particularly in a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

uka

-0.16

ctl

-0.15

alem

-0.15

uela

-0.15

ulta

-0.15

emark

-0.15

 Pale

-0.15

à¤¦à¤°

-0.14

 Maker

-0.14

uten

-0.14

POSITIVE LOGITS

inston

0.16

ìł¤

0.16

âĶĶ

0.16

>NN

0.15

vidence

0.14

ANDOM

0.14

.Interop

0.14

vd

0.14

VD

0.14

ÑģÑĤÑİ

0.14

Activations Density 0.009%

mentions of software, particularly in a professional context

No Comments

No Known Activations