INDEX

Explanations

phrases indicating personal statements or feelings of the speaker

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

idor

-0.19

zew

-0.16

MOTE

-0.15

ãĤĥ

-0.15

 neust

-0.15

ERSION

-0.15

ymi

-0.15

RTOS

-0.14

pedia

-0.14

ERCHANT

-0.14

POSITIVE LOGITS

 going

0.23

 done

0.19

 Going

0.19

 gonna

0.18

 finished

0.18

 sorry

0.18

 tired

0.18

-going

0.17

Going

0.16

 coming

0.16

Activations Density 0.207%

phrases indicating personal statements or feelings of the speaker

No Comments

No Known Activations