INDEX

Explanations

the phrase "the same," indicating repetition or comparison in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lio

-0.17

rious

-0.16

lict

-0.15

ses

-0.15

own

-0.14

cas

-0.14

rac

-0.14

self

-0.14

ogl

-0.13

ict

-0.13

POSITIVE LOGITS

-sex

0.41

 thing

0.39

 exact

0.29

 sort

0.27

 kind

0.26

Thing

0.23

 coisa

0.23

 cosa

0.23

 Thing

0.23

exact

0.22

Activations Density 0.060%

the phrase "the same," indicating repetition or comparison in context

No Comments

No Known Activations