INDEX

Explanations

terms and concepts related to the publishing process

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

anse

-0.15

ÑĥÑĩÐ°Ñģ

-0.15

Zig

-0.15

_ipc

-0.14

ìħĶ

-0.14

asu

-0.14

uries

-0.14

readcr

-0.13

ï

-0.13

oice

-0.13

POSITIVE LOGITS

orre

0.15

 beginnings

0.15

ETA

0.14

 Vers

0.14

_HAVE

0.14

 screenshots

0.14

orado

0.14

 Haupt

0.13

Portal

0.13

YN

0.13

Activations Density 0.002%

terms and concepts related to the publishing process

No Comments

No Known Activations