INDEX

Explanations

terms and phrases related to social and cultural constructs

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

ãĤ©

-0.14

/MIT

-0.14

ãĤ¡

-0.14

meg

-0.13

agu

-0.13

uforia

-0.13

ichten

-0.13

akra

-0.13

amen

-0.12

èĥ½

-0.12

POSITIVE LOGITS

pliers

0.16

0.15

usercontent

0.15

ÙĬØ§ÙĨ

0.14

INA

0.14

(*.

0.14

_attached

0.13

Attachments

0.13

ina

0.13

bedo

0.13

Activations Density 0.022%

terms and phrases related to social and cultural constructs

No Comments

No Known Activations