INDEX

Explanations

phrases related to product offerings and promotions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ustum

-0.16

å¹²

-0.15

_LARGE

-0.15

ionage

-0.15

ahoma

-0.15

urrency

-0.14

avis

-0.14

ÐºÑĢÐ°

-0.14

 å¹

-0.13

afone

-0.13

POSITIVE LOGITS

aa

0.16

_:

0.14

brew

0.14

0.13

ired

0.13

-txt

0.13

LBL

0.13

igne

0.13

imon

0.13

ll

0.13

Activations Density 0.148%

phrases related to product offerings and promotions

No Comments

No Known Activations