INDEX

Explanations

instances of the word "you" and its variations, indicating a focus on second-person perspective or dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

leston

-0.21

are

-0.16

 EITHER

-0.15

fony

-0.14

mani

-0.14

deen

-0.14

exas

-0.14

 either

-0.14

DON

-0.14

ictionaries

-0.14

POSITIVE LOGITS

 perch

0.22

 guys

0.20

 ever

0.19

 suppose

0.19

ë¶Ī

0.17

 remember

0.17

ever

0.16

 remembers

0.16

 supposed

0.15

 mean

0.15

Activations Density 0.070%

instances of the word "you" and its variations, indicating a focus on second-person perspective or dialogue

No Comments

No Known Activations