INDEX

Explanations

variations of the word "give" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ets

-0.17

iegel

-0.16

uga

-0.15

 behalf

-0.15

hu

-0.14

ÑĢÐµÐ¿

-0.14

igel

-0.14

yx

-0.14

hus

-0.14

eya

-0.14

POSITIVE LOGITS

up

0.26

 giving

0.22

 give

0.21

Give

0.20

 gave

0.20

 Give

0.19

ousel

0.19

Giving

0.19

give

0.19

 Giving

0.19

Activations Density 0.048%

variations of the word "give" in different contexts

No Comments

No Known Activations