INDEX

Explanations

specific names, identifiers, and keywords related to businesses and social media interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ril

-0.17

 svens

-0.15

orio

-0.15

 Annie

-0.14

uri

-0.14

å¾½

-0.14

Aly

-0.14

ey

-0.14

reib

-0.14

xEB

-0.14

POSITIVE LOGITS

ica

0.21

ita

0.20

ka

0.20

ela

0.20

enda

0.20

TA

0.19

ja

0.19

ÑĤÐ°

0.19

ia

0.19

Ð»Ð°Ð¶

0.19

Activations Density 0.277%

specific names, identifiers, and keywords related to businesses and social media interactions

No Comments

No Known Activations