INDEX

Explanations

the word "Ly" and its variations, indicating a focus on references to lyrical quality or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Ð»Ð°Ñģ

-0.16

Ð²Ð¾Ð´

-0.16

erti

-0.16

-0.15

éĩı

-0.15

erez

-0.15

haar

-0.15

 caring

-0.14

mut

-0.14

POSITIVE LOGITS

rics

0.24

nda

0.24

ndon

0.23

ric

0.23

dia

0.22

RICS

0.21

cee

0.21

tle

0.20

 hÃ´n

0.19

coming

0.19

Activations Density 0.009%

the word "Ly" and its variations, indicating a focus on references to lyrical quality or related terms

No Comments

No Known Activations