INDEX

Explanations

instances of personal pronouns and first-person narrative statements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ori

-0.14

ubat

-0.14

 seamless

-0.13

ê²©

-0.13

oit

-0.13

tha

-0.13

laps

-0.13

arsed

-0.13

Ele

-0.13

een

-0.13

POSITIVE LOGITS

uja

0.17

aÅ¾

0.16

 finally

0.16

 eventually

0.15

ask

0.15

 arrived

0.15

adia

0.14

ypy

0.14

	TokenName

0.14

 originally

0.14

Activations Density 0.086%

instances of personal pronouns and first-person narrative statements

No Known Activations