INDEX

Explanations

phrases that emphasize connection or association with objects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ãģªãĤĭ

-0.15

Bom

-0.14

.Networking

-0.14

uko

-0.14

_DIAG

-0.13

ors

-0.13

irie

-0.13

andle

-0.13

uality

-0.13

 sitting

-0.13

POSITIVE LOGITS

 nowhere

0.16

 adipiscing

0.15

 intact

0.14

/back

0.14

à¥Ģà¤ıà¤¸

0.14

:title

0.14

iode

0.14

aho

0.14

ntl

0.13

Activations Density 0.119%

phrases that emphasize connection or association with objects or entities

No Comments

No Known Activations