INDEX

Explanations

instances of the word "number" and its variants in various contexts such as statistics and data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bjerg

-0.15

çģ

-0.14

aeper

-0.14

ioctl

-0.13

=%.

-0.13

isinden

-0.13

ç¦ıåĪ©

-0.13

apol

-0.13

å¸¯

-0.13

 âĹĦ

-0.13

POSITIVE LOGITS

Hib

0.16

eless

0.15

Bis

0.15

Hra

0.15

nik

0.14

ahir

0.14

agli

0.14

orden

0.14

 precise

0.14

chw

0.13

Activations Density 0.035%

instances of the word "number" and its variants in various contexts such as statistics and data

No Comments

No Known Activations