INDEX

Explanations

phrases indicating the inclusion or addition of information

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

ling

-0.17

urch

-0.16

iÄħ

-0.15

oding

-0.15

-0.14

isor

-0.14

-many

-0.14

-0.13

xr

-0.13

apon

-0.13

POSITIVE LOGITS

ħį

0.16

 banco

0.15

ibu

0.15

anto

0.14

 Nile

0.14

.spark

0.14

çľī

0.14

akan

0.14

ħ§

0.14

ASN

0.14

Activations Density 0.028%

phrases indicating the inclusion or addition of information

No Comments

No Known Activations

phrases indicating the inclusion or addition of information

No Comments

No Known Activations